19 Commits

Author SHA1 Message Date
4e673dda76 Update the staged implementation plan to address remaining items from the destination policy refactor 2026-06-19 11:25:36 -05:00
cf7e62733e Support catalog maintenance commands 2026-06-19 15:58:36 +00:00
91b72478d5 Update run reporting for catalog workflows 2026-06-19 15:50:09 +00:00
52078e2195 Write catalog state during publish 2026-06-19 15:44:23 +00:00
77cde40296 Add catalog workflow planning 2026-06-19 15:36:26 +00:00
20129bfff5 Add catalog destination state schema 2026-06-19 15:28:03 +00:00
a95662226f Add destination workflow config 2026-06-19 15:18:14 +00:00
d23c624179 Added a roadmap and implementation plan for a significant refactor of pipeline destination policy and catalog state 2026-06-19 10:10:38 -05:00
69043801d0 Update policy for replacement of managed files 2026-06-18 13:38:44 -05:00
8b0ce4d134 Add takeover backend regressions and close roadmap 2026-06-18 15:40:24 +00:00
eba65018be Expose takeover actions in run output 2026-06-18 15:35:06 +00:00
11d1eabe2a Implement shared-root takeover policy 2026-06-18 15:27:50 +00:00
c02106987f Implement single-owner managed takeover 2026-06-18 15:18:38 +00:00
598b665307 Add structured destination comparison details 2026-06-18 15:09:18 +00:00
c4e8ebff6f Add destination takeover config policy 2026-06-18 15:05:09 +00:00
3da7f931b2 Add a feature roadmap and staged implementation plan for configurable levels of managed file overwrite protection 2026-06-18 10:01:20 -05:00
b10a8bd194 Add support for CSS links in generated HTML outputs 2026-06-13 22:16:15 -05:00
c84d8868d1 Fix a bug in the SFTP backend that would cause an error when overwriting existing files 2026-06-13 13:57:50 -05:00
fc33bbca54 Update documentation policy 2026-06-13 13:55:59 -05:00
59 changed files with 3686 additions and 2104 deletions

View File

@@ -292,6 +292,7 @@ Text output is optimized for direct operator use. JSON output is optimized for a
- Usage errors and fatal setup errors exit non-zero and do not emit a JSON result document.
- `run --format json` emits a JSON result for partial destination failures, sets `ok` to `false`, includes result details and errors, and exits non-zero.
- Warnings are included in JSON output and are printed in text output when relevant.
- `run` summaries include separate `replace_older`, `replace_conflict`, `replace_newer`, `replace_takeover`, and `force_replace` counters. Takeover destination actions include `takeover_mode` in JSON and text output.
## Diagnostics And Recovery

View File

@@ -313,6 +313,7 @@ transform:
markdown_to_html:
enabled: true
mode: sidecar
css_href: /assets/report.css
```
`publish.html` controls whether generated HTML outputs are published. When `publish.html` is `true`, `transform.markdown_to_html.enabled` must also be `true`.
@@ -322,10 +323,13 @@ Markdown transform fields:
- `transform.markdown_to_html.enabled`: enables Markdown-to-HTML generation for this destination.
- `transform.markdown_to_html.mode`: optional. Accepted values are `sidecar` and `index`; default is `sidecar` when a Markdown transform block is present.
- `transform.markdown_to_html.input`: optional source manifest path for `index` mode only.
- `transform.markdown_to_html.css_href`: optional stylesheet href to link from generated HTML.
`sidecar` mode renders every manifest-listed `.md` file to a same-directory `.html` output. `index` mode renders one Markdown source to `index.html` at the destination bundle path. If `index` mode omits `input`, the selected source bundle must contain exactly one Markdown file.
At least one output type must be enabled. Enabled Markdown transforms are rejected when `publish.html` is `false`, and `input` is rejected unless `mode` is `index`.
`css_href` may be an absolute `http` or `https` URL, a root-relative path such as `/assets/report.css`, or a relative URL path such as `assets/report.css`. Query strings are allowed. `distributor` injects the href as a `<link rel="stylesheet">` element but does not copy, publish, verify, or manage the CSS file solely because `css_href` is set.
At least one output type must be enabled. Enabled Markdown transforms are rejected when `publish.html` is `false`, `input` is rejected unless `mode` is `index`, and `css_href` is rejected when the Markdown transform is disabled.
## Destination Path Mapping
@@ -412,7 +416,27 @@ pipelines:
mode: sidecar
```
Every output path in a shared root belongs to exactly one `pipeline_id` and `destination_id`. A different owner planning the same path fails as a conflict.
Every output path in a shared root belongs to exactly one `pipeline_id` and `destination_id`. A different owner planning the same path fails as a conflict unless `takeover.mode` allows the managed output path to move to the current owner.
## Takeover Policy
```yaml
takeover:
mode: same_pipeline
```
- `takeover.mode`: optional. Accepted values are `same_pipeline`, `same_source`, `any_managed`, and `never`; default is `same_pipeline`.
Takeover controls when a destination may normally replace valid distributor-managed state whose pipeline, destination, source identity, or shared-root output owner differs from the current publication.
- `same_pipeline`: replace managed state owned by the same pipeline. The previous destination id and source id may differ.
- `same_source`: replace managed state only when the existing source manifest id matches the current source id.
- `any_managed`: replace any valid distributor-managed state at the selected destination bundle path.
- `never`: do not replace identity or source conflicts without the explicit forced replacement workflow.
For shared-root state, `same_pipeline` permits taking over output paths owned by another destination in the same pipeline, `same_source` permits taking over output paths whose owner records the same source manifest id, and `any_managed` permits taking over output paths owned by any valid shared-root owner. Unrelated owner records and non-conflicting outputs remain managed by their existing owners.
Takeover does not apply to unmanaged content, invalid destination state, same-created digest conflicts, or same-source destination-newer comparisons.
## Reconciliation Policy
@@ -486,7 +510,7 @@ Transfer fields and accepted values:
- `transfer.on_destination_newer`: `skip`, `replace`, or `fail`. Default: `skip`.
- `transfer.on_conflict`: `fail` or `replace`. Default: `fail`.
`replace` for `on_destination_newer` and `on_conflict` is honored only when `run --force` is supplied. There is no config field that enables forced replacement by default.
`replace` for `on_destination_newer` and `on_conflict` applies only to valid distributor-managed destination state. Unmanaged destination content and invalid destination state still require the explicit `run --force` workflow where supported.
## Size And Duration Values
@@ -525,6 +549,7 @@ Defaults are applied after YAML decoding and before validation:
- `links.primary: auto` when a `links` block is present and `primary` is omitted
- `state.mode: single_owner`
- `reconciliation.mode: replace`
- `takeover.mode: same_pipeline`
- `retention.prune.enabled: false`
- `transfer.on_destination_same: skip`
- `transfer.on_destination_older: replace`

View File

@@ -96,9 +96,11 @@ Destination reconciliation applies when destination state is older than the sour
- `replace`: for single-owner state, delete managed output paths recorded in `outputs` plus `.distributor.json`, require the destination bundle path to be empty afterward, write the newly planned outputs, and write state whose `outputs` are exactly that new planned set. For shared-root state, delete only the current owner's omitted outputs and preserve unrelated owners.
- `merge`: retain managed output paths omitted from the new plan, overwrite planned paths only when they are already recorded in existing state, fail when a newly planned path exists in storage but is not recorded as managed, and write state whose `outputs` are the cumulative managed set.
Takeover replacement applies when valid managed state has an identity, source, or shared-root output-owner mismatch and destination `takeover.mode` permits the current publication to take ownership. It uses bounded managed replacement behavior. For shared-root state, only taken-over output records and the current owner records are rewritten; unrelated owner records and non-conflicting outputs remain managed by their existing owners.
Top-level `links.primary_url` is selected from the newly planned outputs for the current publication. Retained outputs keep their existing per-output URL metadata.
If a merge publication fails after writing outputs, cleanup removes only newly created outputs from that failed attempt. Previously managed overwritten paths remain managed and are not removed by failed-attempt cleanup.
If a same-source merge publication fails after writing outputs, cleanup removes only newly created outputs from that failed attempt. Previously managed overwritten paths remain managed and are not removed by failed-attempt cleanup. Takeover replacement does not retain omitted outputs through merge reconciliation.
## Comparison Semantics
@@ -106,15 +108,16 @@ If a merge publication fails after writing outputs, cleanup removes only newly c
- No state and no content: publish new outputs.
- No state and existing content: treat the destination as unmanaged.
- Shared-root state without the current owner: publish new outputs for that owner if planned paths do not collide with other owners or unmanaged content.
- Shared-root state without the current owner: publish new outputs for that owner if planned paths do not collide with unmanaged content or with other owners that `takeover.mode` does not permit.
- Matching embedded source manifest: skip.
- Same source id with older `created`: replace if policy allows.
- Same source id with newer `created`: skip by default.
- Same source id and same `created` with different digest: conflict.
- Different source id, pipeline id, or destination id: conflict.
- Same source id with newer `created`: skip by default, or replace when `transfer.on_destination_newer: replace` is configured.
- Same source id and same `created` with different digest: conflict by default, or replace when `transfer.on_conflict: replace` is configured.
- Different source id, pipeline id, or destination id in single-owner state: conflict unless `takeover.mode` permits managed ownership transfer or `transfer.on_conflict: replace` is configured.
- Shared-root output path owned by a different owner: conflict unless `takeover.mode` permits managed ownership transfer or `transfer.on_conflict: replace` is configured.
- Invalid state JSON or invalid state fields: conflict.
Normal single-owner replacement deletes only managed output paths recorded in `outputs` plus `.distributor.json`. Shared-root replacement deletes only omitted outputs for the current owner. Merge publication retains omitted managed outputs. Forced replacement deletes the bounded destination bundle path.
Normal single-owner replacement deletes only managed output paths recorded in `outputs` plus `.distributor.json`. Shared-root replacement deletes only omitted outputs for the current owner. Merge publication retains omitted managed outputs for same-source replacement. Forced replacement deletes the bounded destination bundle path.
## State Repair Semantics
@@ -238,7 +241,7 @@ For shared-root state:
If `state.mode: shared_root` is configured and existing state is a compatible single-owner `.distributor.json` for the same pipeline id and destination id, the next successful publish writes schema version `3` shared-root state for that owner.
If existing single-owner state belongs to a different pipeline or destination, publish fails as a conflict. `distributor` does not implicitly take over unrelated state or unmanaged files.
If `state.mode: shared_root` is configured and existing single-owner state belongs to a different pipeline or destination, publish fails as a conflict. `distributor` does not implicitly convert unrelated single-owner state or take over unmanaged files during shared-root migration.
## Boundaries

View File

@@ -10,7 +10,7 @@ Rendering uses `github.com/yuin/goldmark`. The exact version is pinned in `go.mo
## Renderer Behavior
The transformer constructs `goldmark.New()` with no project-specific extensions, parser options, renderer options, templates, CSS, or metadata injection.
The transformer constructs `goldmark.New()` with no project-specific extensions, parser options, renderer options, templates, or source manifest metadata injection.
Supported output modes:
@@ -19,6 +19,8 @@ Supported output modes:
In `index` mode, `transform.markdown_to_html.input` may name the source manifest path to render. If `input` is omitted, the source manifest must list exactly one `.md` file. The selected input must be a clean relative source path, must be listed in the source manifest, and must end in `.md`.
When `transform.markdown_to_html.css_href` is set, generated HTML includes a stylesheet link in the document head. The href may be an absolute HTTP(S) URL, a root-relative path, or a relative URL path. Distributor treats this as a link reference only; it does not copy, publish, verify, or manage the CSS file solely because `css_href` is configured.
Raw HTML embedded in Markdown is not passed through by the current renderer behavior. Tests allow Goldmark's disabled-or-escaped raw HTML output forms and reject literal script tags in generated HTML.
## HTML Wrapper
@@ -28,10 +30,11 @@ Rendered Markdown body HTML is wrapped in a fixed document shell:
- `<!doctype html>`
- `<html lang="en">`
- UTF-8 `<meta charset>`
- optional `<link rel="stylesheet" href="...">` when `css_href` is configured
- empty `<title>`
- `<body>` containing the rendered Markdown body
The wrapper is deterministic and does not read configuration, templates, CSS, or source manifest metadata.
The wrapper is deterministic. When `css_href` is omitted, the generated wrapper is unchanged from the unstyled output. When `css_href` is configured, its escaped link element is part of the generated output bytes.
## Output Metadata

View File

@@ -52,7 +52,7 @@ The adapter uses these S3 operations:
Writes buffer the input and set `ContentLength`. If no content type is supplied by the caller, the adapter infers a content type from the logical path.
Normal replacement and failed-write cleanup delete only managed output objects plus `.distributor.json`. Merge publication retains omitted managed objects and may overwrite existing managed objects. Forced replacement deletes objects under the bounded destination bundle prefix. The backend does not manage bucket versioning, lifecycle rules, object lock, or delete markers.
Normal replacement and failed-write cleanup delete only managed output objects plus `.distributor.json`. Same-source merge publication retains omitted managed objects and may overwrite existing managed objects. Takeover replacement does not retain omitted outputs through merge reconciliation. Forced replacement deletes objects under the bounded destination bundle prefix. The backend does not manage bucket versioning, lifecycle rules, object lock, or delete markers.
## Error Mapping

View File

@@ -54,7 +54,7 @@ The configured `path` is the backend root. All source discovery, destination pat
The adapter rejects symlink ancestors for reads and writes. Reads require regular files. Writes create parent directories and prefer atomic temp-file-plus-rename writes when requested. Walk output is sorted through the shared storage walker.
Managed cleanup and normal replacement delete only managed output paths plus `.distributor.json`. Merge publication retains omitted managed paths and may overwrite existing managed paths. Forced replacement deletes the bounded destination bundle path.
Managed cleanup and normal replacement delete only managed output paths plus `.distributor.json`. Same-source merge publication retains omitted managed paths and may overwrite existing managed paths. Takeover replacement does not retain omitted outputs through merge reconciliation. Forced replacement deletes the bounded destination bundle path.
## Boundaries

View File

@@ -20,7 +20,7 @@ User-facing command parsing stays in `internal/cli`, including `reconcile-state`
## Config Fields Used
The package consumes the loaded `config.Config`: `server.http`, `secrets.directory`, pipeline ids, source and destination backend fields, validation policy, publish policy, transform policy, path mapping, links, state policy, reconciliation policy, retention policy, and transfer policy.
The package consumes the loaded `config.Config`: `server.http`, `secrets.directory`, pipeline ids, source and destination backend fields, validation policy, publish policy, transform policy, path mapping, links, state policy, reconciliation policy, takeover policy, retention policy, and transfer policy.
Config fields are validated and defaulted by `internal/config` before app workflows use them.
@@ -32,7 +32,7 @@ The app layer registers default transforms, including Markdown-to-HTML, and supp
## State And Manifest Behavior
Run workflows discover and validate source bundles through `internal/bundle`. Destination state actions are prepared and written through `internal/publish` and `internal/state`; the app layer records report projections of those actions and results.
Run workflows discover and validate source bundles through `internal/bundle`. Destination state actions are prepared and written through `internal/publish` and `internal/state`; the app layer records report projections of those actions and results. Run summaries count older-state, conflict, newer-state, takeover, and explicit forced replacements separately.
Reconcile-state workflows load one configured pipeline/destination selector, open that destination root, parse the root `.distributor.json`, and report missing managed output records plus unmanaged storage entries. Managed output existence checks use storage `Stat`; unmanaged reporting uses bounded storage `Walk` and excludes `.distributor.json` plus all paths already recorded as managed. Apply mode removes missing managed output records from state and rewrites valid state only; dry-run reports the same repair without writing. Text output reports `changed`, `would_change`, or `unchanged`; JSON output uses the shared app envelope. It does not validate output digests, delete destination files, adopt unmanaged files, or rewrite invalid or mismatched state.

View File

@@ -18,7 +18,7 @@ The canonical user-facing config reference is `docs/config.md`.
## Config Fields Used
The package defines all user-visible config fields: `server.http`, `secrets`, `pipelines`, source and destination backend fields, validation policy, publish policy, transform policy, path mapping, links, state policy, reconciliation policy, retention policy, and transfer policy.
The package defines all user-visible config fields: `server.http`, `secrets`, `pipelines`, source and destination backend fields, validation policy, publish policy, transform policy, path mapping, links, state policy, reconciliation policy, takeover policy, retention policy, and transfer policy.
## Adapters Used
@@ -26,7 +26,7 @@ No external storage adapters are used directly. The package exposes normalized c
## State And Manifest Behavior
The package does not parse source manifests or destination state. It validates config values that later affect manifest validation and destination state, such as publish/transform combinations, links, state policy, reconciliation policy, retention policy, transfer policy, backend roots, S3 prefix shape, and HTTP upload source settings.
The package does not parse source manifests or destination state. It validates config values that later affect manifest validation and destination state, such as publish/transform combinations, links, state policy, reconciliation policy, takeover policy, retention policy, transfer policy, backend roots, S3 prefix shape, and HTTP upload source settings.
## Skip And Resume Behavior

View File

@@ -8,9 +8,9 @@ Audience: developers and LLM coding agents changing `internal/publish`.
## Inputs And Outputs
Inputs are a source bundle, source backend, destination backend, pipeline id, destination id, destination bundle path, path mapping mode, publish policy, transform policy, optional link policy, state policy, reconciliation policy, transformer resolver, transfer policy, distributor version, and force flag.
Inputs are a source bundle, source backend, destination backend, pipeline id, destination id, destination bundle path, path mapping mode, publish policy, transform policy, optional link policy, state policy, reconciliation policy, takeover policy, transformer resolver, transfer policy, distributor version, and force flag.
Output from planning is a `Plan` with action, reason, destination identity, selected outputs, state mode, owner scope, reconciliation mode, optional existing single-owner or shared-root state, optional primary URL, and force metadata. Shared-root plans also expose other-owner outputs to preserve, current-owner outputs retained by merge, current-owner outputs deleted by replace, and current-owner outputs to write. Execution writes selected source outputs, generated outputs, and `.distributor.json` for executable publish or replacement actions.
Output from planning is a `Plan` with action, reason, destination identity, selected outputs, state mode, owner scope, reconciliation mode, takeover mode, optional existing single-owner or shared-root state, optional primary URL, and force metadata. Shared-root plans also expose other-owner outputs to preserve, taken-over outputs, current-owner outputs retained by merge, current-owner outputs deleted by replace or takeover, and current-owner outputs to write. Execution writes selected source outputs, generated outputs, and `.distributor.json` for executable publish or replacement actions.
## Boundaries
@@ -20,7 +20,7 @@ External destination state semantics are documented in `docs/integrations/destin
## Config Fields Used
The package consumes already-defaulted config values for destination `publish`, `transform`, `links`, `state`, `reconciliation`, `transfer`, and path mapping mode. It uses `config.ValidatePublishTransformPolicy` for publish/transform consistency.
The package consumes already-defaulted config values for destination `publish`, `transform`, `links`, `state`, `reconciliation`, `takeover`, `transfer`, and path mapping mode. It uses `config.ValidatePublishTransformPolicy` for publish/transform consistency.
## Adapters Used
@@ -28,25 +28,25 @@ The package depends on `internal/storage.Backend` for source and destination IO,
## State And Manifest Behavior
Planning inspects destination state through `internal/state`, compares it with the source manifest, and maps comparison outcomes plus transfer policy into actions: `publish_new`, `replace_older`, `force_replace`, `skip_same`, `skip_destination_newer`, `fail_conflict`, or `fail_unmanaged`.
Planning inspects destination state through `internal/state`, compares it with the source manifest, and maps comparison outcomes plus transfer and takeover policy into actions: `publish_new`, `replace_older`, `replace_conflict`, `replace_newer`, `replace_takeover`, `force_replace`, `skip_same`, `skip_destination_newer`, `fail_conflict`, or `fail_unmanaged`.
Single-owner destinations compare the whole destination state against the configured pipeline and destination ids. Shared-root destinations compare only the current owner scope, keyed by pipeline id and destination id. An absent shared-root owner is publishable for that owner unless a planned output collides with unmanaged storage content. Planned writes to a path owned by another shared-root owner fail as conflicts.
Single-owner destinations compare the whole destination state against the configured pipeline and destination ids. Valid managed identity and source conflicts can become `replace_takeover` when `takeover.mode` allows them. Shared-root destinations compare only the current owner scope, keyed by pipeline id and destination id. An absent shared-root owner is publishable for that owner unless a planned output collides with unmanaged storage content. Planned writes to a path owned by another shared-root owner become `replace_takeover` when `takeover.mode` allows that managed output path to move to the current owner.
Execution writes destination state after selected outputs are written. Destination state includes copied source output metadata, generated output metadata, output timestamps, embedded source manifest, reconciliation metadata, link metadata when configured, pipeline id, destination id, and publication timestamps.
## Skip And Resume Behavior
`skip_same` and `skip_destination_newer` execute as no-ops. Replacement-mode single-owner updates remove managed output paths from existing state plus `.distributor.json`, verify the destination is empty, and write state whose outputs are exactly the new plan. Replacement-mode shared-root updates remove only current-owner omitted outputs and preserve unrelated owners. Merge-mode updates retain omitted managed outputs, overwrite only paths already recorded as managed, reject unmanaged destination path collisions, and write cumulative output state. Failed writes trigger cleanup where practical; merge cleanup removes only newly created outputs from the failed attempt.
`skip_same` and `skip_destination_newer` execute as no-ops. Replacement-mode single-owner updates remove managed output paths from existing state plus `.distributor.json`, verify the destination is empty, and write state whose outputs are exactly the new plan. `replace_conflict` uses managed replacement mechanics and does not retain omitted outputs through merge reconciliation. `replace_newer` follows the same managed replacement and merge-retention rules as `replace_older`. `replace_takeover` uses managed replacement mechanics and does not retain omitted outputs through merge reconciliation. Replacement-mode shared-root updates remove only current-owner omitted outputs and preserve unrelated owners. Shared-root takeover rewrites only the taken-over output records and current owner records. Merge-mode same-source updates retain omitted managed outputs, overwrite only paths already recorded as managed, reject unmanaged destination path collisions, and write cumulative output state. Failed writes trigger cleanup where practical; same-source merge cleanup removes only newly created outputs from the failed attempt.
Shared-root execution writes schema version `3` state. It preserves unrelated owner records and outputs, updates only the publishing owner metadata, preserves root `created_at`, and updates root `updated_at` after successful state writes. Compatible single-owner state for the same pipeline and destination is converted to shared-root state on successful publish.
Forced replacement is explicit per request and deletes the bounded destination bundle path before writing new outputs and state.
Forced replacement is explicit per request and deletes the bounded destination bundle path before writing new outputs and state. Valid managed conflict and newer-state replacements are normal managed replacement actions when transfer policy allows them; they are not forced replacement actions.
Retention pruning is not part of publish execution and does not run automatically after a successful publish. The app-level prune workflow uses destination state after publication to select managed outputs for deletion.
## Failure Behavior
Planning fails for incomplete requests, invalid publish/transform policy, invalid state mode, invalid reconciliation mode, output path collisions, invalid destination state, unmanaged destination content without force, shared-root owner path conflicts, conflict outcomes not allowed by transfer policy, unresolved transforms, invalid Markdown output selection, and invalid link URL planning.
Planning fails for incomplete requests, invalid publish/transform policy, invalid state mode, invalid reconciliation mode, output path collisions, invalid destination state, unmanaged destination content without force, shared-root owner path conflicts not allowed by `takeover.mode`, conflict outcomes not allowed by transfer policy, unresolved transforms, invalid Markdown output selection, and invalid link URL planning.
Execution fails on delete, read, transform output, unmanaged merge path collision, shared-root ownership conflict, write, state validation, state serialization, or context errors. Execution refuses actions that are not executable publish or replacement actions.
@@ -65,7 +65,7 @@ Execution fails on delete, read, transform output, unmanaged merge path collisio
- Replacement reconciliation deletes only managed paths recorded in existing state plus `.distributor.json` for single-owner state, and only current-owner omitted outputs for shared-root state.
- Merge reconciliation never adopts unmanaged content.
- Merge state output records are cumulative for the single owner.
- Shared-root planning is owner-scoped and preserves unrelated owner outputs.
- Shared-root planning is owner-scoped, preserves unrelated owner outputs, and records taken-over managed output paths separately from unrelated owners.
- Shared-root execution writes owner-scoped changes without deleting unrelated owners.
- Forced replacement deletes only within the supplied destination bundle path.
- Destination state is written after selected outputs are written.

View File

@@ -44,7 +44,7 @@ Shared-root helper projections preserve output `created_at` for existing managed
## Skip And Resume Behavior
Comparison is pure. It returns outcomes for absent state, unmanaged content, invalid state, pipeline/destination mismatch, same source manifest, older destination, newer destination, same-created digest conflict, and different source id conflict. It does not decide whether to skip, replace, force, or fail; publish planning maps outcomes to actions.
Comparison is pure. It returns outcomes for absent state, unmanaged content, invalid state, pipeline/destination mismatch, same source manifest, older destination, newer destination, same-created digest conflict, and different source id conflict. Shared-root helpers expose structured output ownership conflicts. State code does not decide whether to skip, replace, take over, force, or fail; publish planning maps outcomes and conflicts to actions.
Shared-root comparison is owner-scoped. It compares only the owner keyed by the current pipeline id and destination id, treats an absent owner as absent destination state for that owner, and can compare compatible single-owner state for the current owner without converting unrelated single-owner state.
@@ -74,7 +74,7 @@ Parsing rejects invalid JSON, trailing data, missing required fields, invalid ti
- Newly written single-owner state uses schema version `2`.
- Schema version `1` state remains readable as replacement-mode single-owner state.
- Schema version `3` shared-root state is parsed and validated without converting unrelated single-owner state.
- Shared-root owner updates preserve unrelated owners and reject planned path collisions with other owners.
- Shared-root owner updates preserve unrelated owners. Publish planning removes taken-over output records before owner replacement when takeover policy allows a managed path to move owners.
- Missing-output repair helpers preserve unrelated owner records and outputs.
- Prune planning uses output `updated_at` and preserves unrelated shared-root owners.
- Generated outputs always record a transform id.

View File

@@ -67,11 +67,16 @@ Published destination bundle paths contain `.distributor.json`. See [Destination
- No destination state and no destination content: publish new outputs.
- Matching destination state: skip as already published.
- Older destination state for the same source id: replace if transfer policy allows it.
- Newer destination state: skip by default.
- Invalid destination state, identity mismatch, different source id, or same-created digest mismatch: fail by default.
- Newer destination state for the same source id: skip by default, or replace when `transfer.on_destination_newer: replace` is configured.
- Valid managed state with an identity, source, same-created digest, or shared-root output-owner mismatch: replace when destination `takeover.mode` allows it or, for remaining valid managed conflicts, when `transfer.on_conflict: replace` is configured.
- Invalid destination state, identity, source, same-created digest, or shared-root output-owner mismatches not allowed by `takeover.mode` or `transfer.on_conflict: replace`: fail by default.
- Content without `.distributor.json`: fail as unmanaged content by default.
When destination state is older than the source, `transfer.on_destination_older` controls whether publication may proceed and `reconciliation.mode` controls how managed outputs are updated.
When destination state is older or newer than the source, `transfer.on_destination_older` and `transfer.on_destination_newer` control whether publication may proceed and `reconciliation.mode` controls how managed outputs are updated.
When `transfer.on_conflict: replace` permits `replace_conflict`, the destination is valid managed state but does not match the current source, pipeline, destination, or same-created digest. `replace_conflict` rewrites the affected managed destination state and does not retain omitted outputs through merge reconciliation.
For takeover replacement, `reconciliation.mode: merge` does not retain omitted outputs from the previous source identity. The destination is rewritten as a managed replacement for the current source or shared-root owner.
`reconciliation.mode: replace` is the default. It deletes only managed output paths recorded in `.distributor.json` plus the state file, verifies the destination bundle path is empty, then writes the newly planned outputs and state. The new state `outputs` array is exactly the newly planned output set.
@@ -79,11 +84,11 @@ When destination state is older than the source, `transfer.on_destination_older`
For both modes, retained or overwritten paths are identified only from `.distributor.json`; unmanaged files are not adopted.
For `state.mode: shared_root`, one destination root may contain outputs from multiple pipeline/destination owners. Comparisons, replacement, and merge retention are scoped to the current owner. Outputs owned by other owners are preserved. A planned output path owned by another owner fails as a conflict, and a planned path that exists in storage but is not recorded in state fails as unmanaged content by default.
For `state.mode: shared_root`, one destination root may contain outputs from multiple pipeline/destination owners. Comparisons, replacement, and merge retention are scoped to the current owner. Outputs owned by other owners are preserved unless a planned output path is owned by another valid owner and `takeover.mode` allows moving that path to the current owner. A planned path that exists in storage but is not recorded in state fails as unmanaged content by default.
If `state.mode: shared_root` is configured on a destination whose existing single-owner state belongs to the same pipeline and destination, the next successful publish converts that state file to shared-root schema. Existing single-owner state for a different pipeline or destination remains a conflict.
If a write fails after some outputs were written, `distributor` attempts cleanup before returning the error. In `replace` mode, cleanup removes outputs written during that failed attempt. In `merge` mode, cleanup removes only newly created outputs from that failed attempt; overwritten managed outputs are left in place because they previously belonged to the managed set. Operators should still inspect the destination after a failed write before retrying.
If a write fails after some outputs were written, `distributor` attempts cleanup before returning the error. In `replace` mode and takeover replacement, cleanup removes outputs written during that failed attempt. In same-source `merge` mode, cleanup removes only newly created outputs from that failed attempt; overwritten managed outputs are left in place because they previously belonged to the managed set. Operators should still inspect the destination after a failed write before retrying.
Fan-out destinations are independent. If one destination fails after planning or execution begins, later destinations are still attempted. The command exits non-zero if any destination failed.
@@ -150,12 +155,15 @@ For single-owner state, the state owner must match the selected pipeline and des
`run --dry-run` loads config, resolves credentials, discovers source bundles, opens destinations, inspects destination state, builds publish plans, and prints actions. It does not write outputs, `.distributor.json`, or SSH `known_hosts` entries. For reconciliation, dry runs report the same high-level action labels as execution; inspect the configured destination's `reconciliation.mode` to determine whether `replace_older` will replace the managed set or merge into it.
For shared-root destinations, dry runs are owner-scoped. A `replace_older` action replaces or merges only the current owner according to `reconciliation.mode`; unrelated owners remain managed by the shared-root state.
For shared-root destinations, dry runs are owner-scoped. A `replace_older` action replaces or merges only the current owner according to `reconciliation.mode`; unrelated owners remain managed by the shared-root state. Paths owned by another owner fail as conflicts unless `takeover.mode` allows ownership transfer.
Review these action labels before publishing:
- `publish_new`: destination state is absent, or a shared-root owner is absent and planned paths are publishable.
- `replace_older`: destination state is older than the source.
- `replace_newer`: destination state is newer than the source and `transfer.on_destination_newer: replace` allows managed replacement.
- `replace_conflict`: destination state is valid managed state with a conflict and `transfer.on_conflict: replace` allows managed replacement.
- `replace_takeover`: destination state is valid managed state and `takeover.mode` allows replacement across an identity, source, or shared-root output-owner mismatch.
- `skip_same`: destination state already matches the source.
- `skip_destination_newer`: destination state is newer than the source and is skipped.
- `force_replace`: destructive replacement selected because `--force` is present and policy permits it.
@@ -163,7 +171,7 @@ Review these action labels before publishing:
Fixed destinations add fixed-path warnings during dry runs, including the selected source bundle and replacement warnings when the destination root would be replaced.
JSON output includes warnings, pipeline summaries, destination action records, output records, URLs when configured, final counters, and partial failure details. Fatal setup failures such as unreadable config or invalid secrets do not produce a JSON result document.
Text and JSON summaries count `publish_new`, `replace_older`, `replace_conflict`, `replace_newer`, `replace_takeover`, `force_replace`, skipped, and failed destinations separately. Takeover action records include the configured takeover mode and the conflict reason. JSON output includes warnings, pipeline summaries, destination action records, output records, URLs when configured, final counters, and partial failure details. Fatal setup failures such as unreadable config or invalid secrets do not produce a JSON result document.
## Forced Replacement Workflow
@@ -174,10 +182,7 @@ go run ./cmd/distributor run --config <config-path> --dry-run --force
go run ./cmd/distributor run --config <config-path> --force
```
Forced replacement can claim unmanaged non-empty destination paths. State conflicts require both `--force` and transfer policy that permits replacement:
- newer destination state requires `transfer.on_destination_newer: replace`;
- conflict outcomes require `transfer.on_conflict: replace`.
Forced replacement can claim unmanaged non-empty destination paths and is reserved for exceptional destructive replacement. Valid managed newer state and valid managed conflict state use `replace_newer` and `replace_conflict` when the corresponding transfer policy allows replacement; they do not require `--force`.
Forced replacement deletes the current destination bundle path before writing outputs and state. It does not delete parent paths, sibling paths, or storage outside the destination bundle path. For fixed destinations, the destination bundle path is the backend root, so a forced replacement can clear that configured root.
@@ -267,7 +272,7 @@ S3 execution uses the AWS SDK for Go v2. See [S3-Compatible Storage Integration]
When explicit S3 credential variable names are configured, both must resolve to non-empty values through the process environment or `secrets.directory`. When omitted, the AWS SDK default credential chain is used as-is.
Normal single-owner replacement and failed-write cleanup delete only managed output objects recorded in `.distributor.json` plus the state object. Shared-root replacement deletes only current-owner omitted output objects and rewrites the shared state object. Merge publication retains omitted managed objects and may overwrite existing managed objects. Forced replacement deletes objects under the bounded destination bundle prefix. Distributor does not manage bucket versioning or delete markers.
Normal single-owner replacement and failed-write cleanup delete only managed output objects recorded in `.distributor.json` plus the state object. Shared-root replacement deletes only current-owner omitted output objects and rewrites the shared state object. Same-source merge publication retains omitted managed objects and may overwrite existing managed objects. Takeover replacement does not retain omitted outputs through merge reconciliation. Forced replacement deletes objects under the bounded destination bundle prefix. Distributor does not manage bucket versioning or delete markers.
## Secrets Operation
@@ -282,7 +287,7 @@ Use these recovery boundaries:
- For source validation failures, regenerate the source bundle and manifest together.
- For an empty or missing destination, rerun after fixing config or storage access.
- For unmanaged destination content, move unrelated files aside or use a different destination path before publishing.
- For shared-root ownership conflicts, change one owner so it writes a different destination path, or use a separate destination root.
- For shared-root ownership conflicts, change one owner so it writes a different destination path, use a separate destination root, or configure `takeover.mode` when the current owner should take over valid managed output paths.
- For missing managed output files recorded in state, run `reconcile-state --dry-run`, then apply `reconcile-state` if the missing files should no longer be considered managed.
- For configured retention cleanup, run `prune --dry-run`, then apply `prune --apply` after reviewing the managed output list.
- For failed writes, inspect the destination bundle path, remove only confirmed partial outputs if needed, then rerun `--dry-run`. In merge mode, retained outputs may be intentional managed outputs from the prior state.

View File

@@ -169,9 +169,9 @@ Destination comparison rules are based on `.distributor.json`:
- No `.distributor.json`: publish normally only if the destination bundle path is empty.
- Existing state embeds the same normalized source manifest: skip as already published.
- Existing state has the same source id and an older source `created`: replace, subject to destructive-operation safety rules.
- Existing state has the same source id and a newer source `created`: skip because the destination is newer than the source.
- Existing state has the same source id and same `created` but different digest: fail as a conflict.
- Existing state has a different source id: fail as a conflict.
- Existing state has the same source id and a newer source `created`: skip by default, or replace when `transfer.on_destination_newer: replace` is configured.
- Existing state has the same source id and same `created` but different digest: fail by default, or replace as valid managed conflict state when `transfer.on_conflict: replace` is configured.
- Existing valid managed state has a different source id, pipeline id, destination id, or shared-root output owner: replace when destination `takeover.mode` permits that ownership transfer, or replace as valid managed conflict state when `transfer.on_conflict: replace` is configured; otherwise fail as a conflict.
For older destination state, destination `reconciliation.mode` controls output updates. `replace` rewrites the managed output set to match the new plan. `merge` retains omitted managed outputs, overwrites only existing managed paths, and rejects planned paths that collide with unmanaged storage content.
@@ -264,6 +264,7 @@ Pipeline configuration should express:
- per-destination transform policy;
- per-destination public link policy;
- validation behavior;
- per-destination takeover behavior;
- destination conflict/replacement behavior.
## Modules and Registries

View File

@@ -18,7 +18,7 @@ Use it with `docs/policy/architecture.md` and `docs/policy/documentation.md`.
- `internal/adapters/ssh`: SSH/SFTP backend.
- `internal/adapters/s3`: S3-compatible object storage backend.
- `internal/storage/fake`: in-memory backend for tests.
- `internal/publish`: destination inspection, output planning, reconciliation, execution, managed cleanup, and explicit forced replacement.
- `internal/publish`: destination inspection, output planning, takeover planning, reconciliation, execution, managed cleanup, and explicit forced replacement.
- `internal/transform`: transform interface and registry.
- `internal/transform/markdown`: Markdown-to-HTML transform.
- `internal/notify`: notification interface and current no-op notifier.

View File

@@ -43,6 +43,7 @@ Canonical homes:
- project purpose and quickstart: `README.md`
- development principles: `docs/policy/architecture.md`
- public HTTP API reference: `docs/api.md`
- configuration reference: `docs/config.md`
- CLI reference: `docs/cli.md`
- operations and recovery: `docs/operations.md`
@@ -122,6 +123,22 @@ Recommended:
- `docs/troubleshooting.md`
- validated examples under `examples/`
### Public HTTP API service
Required:
- `docs/api.md`
- `docs/cli.md`, if CLI-based
- `docs/config.md`, if config-driven
- `docs/operations.md`
- `docs/internal/`
- `docs/policy/development.md`
Recommended:
- `docs/troubleshooting.md`
- `docs/consumers/`, for task-oriented client integration guides
- `docs/integrations/`, for upstream/downstream service contracts
- validated examples under `examples/`
### Project with public packages or consumer APIs
Required:
@@ -173,6 +190,32 @@ It should include:
For small projects, this file may be brief. It may simply state that the project is intentionally narrow, monolithic, and dependency-light.
### docs/api.md
**Audience:** external HTTP API consumers, developers, LLM coding agents integrating by HTTP
Required for projects whose primary public interface is HTTP.
`docs/api.md` is the canonical public HTTP API contract. It should be normative for external consumers and should not be duplicated by README, operations docs, consumer guides, or integration docs.
It should include:
1. base URL conventions;
2. authentication and authorization behavior, if implemented;
3. response envelope;
4. supported media types and content negotiation behavior;
5. shared query parameters;
6. endpoint reference grouped by route family;
7. request parameters and validation rules;
8. response fields, units, nullability, and optionality;
9. error response shape and status codes;
10. pagination, caching, rate-limit, idempotency, and retry behavior, if implemented;
11. compact request and response examples.
It must document only implemented endpoints and behavior. Planned endpoints, proposed fields, future filters, and experimental response shapes belong only under `docs/roadmap/`.
For HTTP API projects, `docs/consumers/` may provide task-oriented client integration guides, but those guides should link to `docs/api.md` for the authoritative endpoint contract.
### docs/policy/development.md
**Audience:** developers, LLM coding agents
@@ -264,6 +307,8 @@ Required for projects with public packages, SDKs, client APIs, plugin APIs, or o
This directory describes how an external codebase should consume the project's public API. It should be task-oriented and copyable where useful. It is not the place for internal implementation details or operator procedures.
For projects whose public API is HTTP, `docs/consumers/` is not required, and it should not duplicate the endpoint reference in `docs/api.md`. If present, it may provide practical integration workflows, client-specific examples, or migration notes that link back to `docs/api.md`.
`docs/consumers/api.md` should provide the consumer-facing overview and primary implementation workflow. It should include:
1. intended consumer audience and use cases;
@@ -330,6 +375,8 @@ Required for projects that depend on external CLIs, APIs, services, protocols, o
This directory contains concise, versioned reference notes for external integration contracts. It should document only the parts of the external system that this project actually uses or exposes.
For public HTTP API services, `docs/integrations/` should document upstream, downstream, storage, protocol, or runtime contracts that the service depends on or bridges. It should not become a second copy of the public HTTP endpoint reference; that belongs in `docs/api.md`.
Use one file per integration where useful.
## Examples Directory
@@ -385,9 +432,10 @@ Before merging documentation changes, verify:
- README is concise and orientation-focused.
- `docs/policy/architecture.md` describes development principles.
- `docs/api.md` is the canonical HTTP contract for HTTP API services.
- Future work appears only under `docs/roadmap/`.
- User-facing docs avoid unnecessary internals.
- Consumer-facing docs explain public APIs without duplicating integration contracts.
- Consumer-facing docs explain public APIs without duplicating HTTP endpoint or integration contracts.
- Developer-facing docs preserve boundaries and invariants.
- Config examples match the schema.
- CLI examples match real commands and flags.

283
docs/roadmap/catalog.md Normal file
View File

@@ -0,0 +1,283 @@
# Catalog State And Destination Workflow Roadmap
This roadmap records the intended first-class state model and destination
workflow configuration for replacement and additive publication workflows.
Current `single_owner` and `shared_root` state are oriented around comparing a
destination owner to one latest source manifest. That works well for replacement
workflows, where a producer maintains a curated source of truth and
`distributor` makes a destination match it. It is a poor fit for additive
workflows, where each run contributes new or updated output paths while
preserving unrelated managed outputs from previous runs and other pipelines.
The target model is a current-state catalog: `.distributor.json` records the
currently managed output paths at a destination root, and each output record
stores its current owner, compact source identity, content digest, and update
metadata. It is not intended to be an audit log.
Both replacement and additive workflows should use the same catalog state shape.
The workflow choice is runtime policy from destination config, not persisted
state.
## Locked Decisions
- Add one destination state mode named `catalog` for both replacement and
additive workflows.
- Catalog state writes `.distributor.json` schema version `4`.
- Add a destination-level `workflow` setting with accepted values
`replacement` and `additive`.
- Default `workflow` to `additive` because it is the least destructive workflow.
- `workflow` replaces the normal user-facing need to combine `state.mode`,
`reconciliation.mode`, `takeover.mode`, and transfer conflict settings for the
two primary workflows.
- `workflow: replacement` treats the current planned outputs as the authoritative
managed output set for the destination scope and removes previously managed
outputs in that scope when they are no longer planned.
- `workflow: additive` writes or overwrites the planned output paths and retains
unrelated managed outputs.
- If a planned path already exists as a managed output, the new publication may
overwrite it and becomes that path's current owner.
- If a planned path exists in storage but is not recorded in valid catalog state,
it remains unmanaged content and must not be adopted implicitly.
- If an output path changes owner, preserve the output record's existing
`created_at` and update only `updated_at`.
- Catalog state records current ownership only. It does not retain historical
owners, historical sources, or old versions of overwritten output records.
- `pipeline_id` and `destination_id` are stored separately on each output
record. They are not concatenated into one owner string.
- Catalog state does not include top-level `owners`; owners are derivable from
the output records.
- Catalog state does not include top-level `sources`; compact source identity is
stored directly on each output record.
- Catalog state does not record whether the last run used `replacement` or
`additive`. Workflow is execution policy, and persisting it would create
drift risk if config changes later.
- Legacy destination policy fields should be rejected outright in the new
workflow config model. Do not retain aliases for `state`, `reconciliation`,
`takeover`, or `transfer`.
## Destination Workflow Semantics
The user-facing destination config should express intent directly:
```yaml
destinations:
- id: weather-latest
backend: local
path: /srv/reports/weather/latest
workflow: additive
```
```yaml
destinations:
- id: weather-archive
backend: local
path: /srv/reports/weather/archive
workflow: replacement
```
`workflow` is orthogonal to backend config, path mapping, publish source/HTML
selection, transforms, links, and retention.
### Replacement Workflow
A replacement destination is for producers that maintain a curated source of
truth and expect `distributor` to make the destination's managed scope match the
current publication.
For a destination configured with `workflow: replacement`:
- planned outputs are written to their resolved destination paths;
- planned outputs may overwrite existing managed outputs at the same path;
- each written output record is replaced in-place with the current
publication's owner, source identity, hash, size, and timestamps;
- managed outputs in the destination scope that are not present in the current
plan are deleted and removed from catalog state;
- unmanaged destination content remains unmanaged and blocks planned path
collisions unless an explicit force workflow later chooses otherwise;
- the catalog state shape remains the same as additive workflow state.
### Additive Workflow
An additive destination is for producers that routinely contribute outputs to a
shared destination root.
For a destination configured with `workflow: additive`:
- planned outputs are written to their resolved destination paths;
- planned outputs may overwrite existing managed outputs at the same path;
- each overwritten output record is replaced in-place with the current
publication's owner, source identity, hash, size, and timestamps;
- managed outputs not present in the current plan are retained;
- unrelated managed outputs from other pipelines or destinations are retained;
- unmanaged destination content remains unmanaged and blocks planned path
collisions unless an explicit force workflow later chooses otherwise;
- pruning can select retained managed outputs by `updated_at` and, when useful,
by `pipeline_id` and/or `destination_id`.
Replacement workflow treats the current publication as the desired managed
output set for a destination scope. Additive workflow treats the current
publication as a patch to the catalog of currently managed outputs.
## Destination State Schema Version 4
Catalog state should use this top-level shape:
```json
{
"schema_version": 4,
"distributor_version": "dev",
"created_at": "2026-06-19T12:00:00Z",
"updated_at": "2026-06-19T12:05:00Z",
"state": {
"mode": "catalog"
},
"outputs": []
}
```
Top-level fields:
- `schema_version`: required. Value `4` for catalog state.
- `distributor_version`: optional diagnostic version string.
- `created_at`: required RFC3339 timestamp for when the catalog state file was
first created.
- `updated_at`: required RFC3339 timestamp for the latest catalog state update.
- `state.mode`: required. Value `catalog`.
- `outputs`: required array of currently managed output records.
Catalog state should not include top-level `pipeline_id`, `destination_id`,
`published_at`, `workflow`, `owners`, `sources`, or a full source manifest.
Those concepts belong on output records or in configuration.
## Output Record Schema
Each output record should be self-contained enough to support current
ownership, pruning, repair, bitrot checks, and basic provenance without a
separate owner or source catalog.
```json
{
"path": "tomorrow/index.html",
"pipeline_id": "weatherreporter.daily",
"destination_id": "latest-html",
"source": {
"id": "weatherreporter.tomorrow",
"digest": "sha256:0123456789abcdef0123456789abcdef0123456789abcdef0123456789abcdef",
"created": "2026-06-19T12:00:00Z"
},
"kind": "generated",
"source_path": "report.md",
"transform": "markdown_to_html",
"sha256": "sha256:abcdef0123456789abcdef0123456789abcdef0123456789abcdef0123456789",
"size": 12345,
"created_at": "2026-06-19T12:00:00Z",
"updated_at": "2026-06-19T12:05:00Z",
"url": "https://reports.example.com/weather/tomorrow/"
}
```
Required output fields:
- `path`: destination-relative managed output path.
- `pipeline_id`: pipeline that most recently wrote this output path.
- `destination_id`: destination that most recently wrote this output path.
- `source`: compact identity of the source bundle that produced this output.
- `source.id`: source manifest id.
- `source.digest`: source manifest digest.
- `source.created`: source manifest creation timestamp, RFC3339.
- `kind`: `source` or `generated`.
- `sha256`: digest of the output bytes.
- `size`: output byte size.
- `created_at`: RFC3339 timestamp for when this output path first became
managed in catalog state.
- `updated_at`: RFC3339 timestamp for when this output path was most recently
written or updated.
Optional output fields:
- `source_path`: present only for generated outputs; source manifest path used
to produce the generated output.
- `transform`: present only for generated outputs; transform name used to
produce the generated output.
- `url`: present only when destination link configuration produces a public URL
for this output.
For copied source outputs, `source_path` and `transform` should be omitted. The
output `path` is already the copied source artifact path.
## Useful Properties
The catalog shape supports both primary workflows without unnecessary
normalization:
- current owner of each path is explicit;
- current source identity for each path is explicit;
- bitrot checks can compare storage bytes to `sha256`;
- pruning can use `updated_at`, optionally scoped by `pipeline_id` and
`destination_id`;
- repair can remove missing managed output records without consulting an owner
or source table;
- overwriting an output path updates one output record in place;
- no orphaned top-level owner/source records need to be maintained.
The schema intentionally avoids storing a full source manifest for every output.
The source manifest remains the producer-to-distributor validation contract, but
catalog state only needs compact source identity for currently managed outputs.
## Relationship To Existing State And Config Modes
Existing state modes remain current behavior until catalog mode is implemented:
- `single_owner` schema version `2` supports one owner for a destination bundle
path.
- `shared_root` schema version `3` supports multiple owners in one destination
root but still keeps owner records with latest source manifests.
- `catalog` schema version `4` should support replacement and additive
current-state ownership without top-level owner or source catalogs.
The intended user-facing config should move toward `workflow: replacement` and
`workflow: additive` instead of requiring ordinary users to combine
`state.mode`, `reconciliation.mode`, `takeover.mode`, and transfer conflict
settings.
Because the project is still alpha pre-release, catalog implementation should be
a clean break:
- remove legacy write paths for current `single_owner` and `shared_root` state;
- do not implement migration from schema versions `1`, `2`, or `3`;
- do not preserve backwards compatibility for legacy destination state;
- when a configured destination writes successfully, write schema version `4`
catalog state;
- if an existing `.distributor.json` has schema version lower than `4`, treat it
as superseded legacy state for planning purposes and overwrite it according to
the configured workflow, without attempting conversion.
For the first catalog run against superseded legacy state:
- `workflow: replacement` may clear the bounded destination root before writing
the planned outputs and schema version `4` catalog state.
- `workflow: additive` may overwrite only the planned output paths, then write
schema version `4` catalog state containing those planned outputs.
- unplanned files left behind by an additive run against superseded legacy state
are not recorded in catalog state and are treated as unmanaged content by
later catalog runs.
The target direction is that both primary workflows use catalog state.
## Prune And Reconcile-State Scope
Catalog maintenance commands should initially keep the existing ownership
selector model:
- `prune --pipeline <id> --destination <id>` operates only on outputs currently
owned by that pipeline/destination.
- `reconcile-state --pipeline <id> --destination <id>` repairs only outputs
currently owned by that pipeline/destination.
- `reconcile-state --all-owners` repairs all output records in the catalog.
- `prune` remains scoped to the selected pipeline/destination owner only in the
initial catalog implementation.
Do not add catalog-specific selectors in the initial implementation, such as
`--source-id`, `--path-prefix`, or `--kind`. Those may be useful later, but they
are not required to make additive workflow first-class.

View File

@@ -0,0 +1,399 @@
# Catalog Follow-Up Implementation Roadmap
This is the active staged plan for closing the remaining catalog-state
implementation gaps found after the schema version `4` catalog workflow landed.
It supersedes the earlier catalog implementation plan.
The current code already supports destination `workflow: additive` and
`workflow: replacement`, writes catalog state schema version `4`, rejects legacy
destination policy YAML fields, and routes publish execution through catalog
planning for normal runs. The remaining work is to make the implemented behavior
release-ready: restore a meaningful catalog `--force` path, synchronize current
docs and examples, and remove legacy single-owner/shared-root implementation
debt.
## Current Baseline
- Destination config accepts `workflow: additive` and `workflow: replacement`.
- Omitted `workflow` defaults to `additive`.
- Destination YAML fields `state`, `reconciliation`, `takeover`, and `transfer`
are rejected by strict YAML decoding.
- Successful publish writes `.distributor.json` schema version `4` with
`state.mode: catalog`.
- Schema versions `1`, `2`, and `3` are treated as superseded legacy state for
publish planning.
- `run --force` remains in the CLI and docs, but catalog publish planning does
not currently select `force_replace`.
- Current docs and examples still describe legacy config/state behavior in
several places.
- Legacy single-owner and shared-root state types, tests, and execution helpers
remain in the codebase even though normal publish planning no longer uses
them.
## Implementation Principles
- Preserve the catalog state shape defined in `docs/roadmap/catalog.md`.
- Keep `workflow` as runtime config policy; do not persist it in
`.distributor.json`.
- Keep unmanaged content protected by default.
- Keep `--force` explicit, per-run, dry-runnable, and bounded to the configured
destination bundle path.
- Do not reintroduce legacy config aliases or compatibility migration.
- Keep backend adapters unaware of catalog, workflow, and force policy.
- Update current-behavior docs in the same stage that makes the described
behavior true.
## Active Implementation Stages
## Stage 1: Catalog Force Planning And Execution
Goal: make `run --force` meaningful for catalog workflows while keeping normal
catalog safety conservative.
Implementation scope:
- Update `internal/publish` planning so `req.Force` can select
`force_replace` for exceptional destructive catalog cases.
- Force should apply to these cases:
- no valid `.distributor.json` and destination bundle path has unmanaged
content;
- planned path collision with storage content not recorded in valid catalog
state;
- invalid destination state JSON or invalid destination state fields;
- unsupported future destination state schema, if the operator explicitly
chooses force replacement after dry-run review.
- Force should not be needed for ordinary valid catalog-managed upserts or
replacements. Additive and replacement workflow behavior remains normal managed
behavior.
- `force_replace` must delete only the bounded destination bundle path through
the storage abstraction, then write planned outputs and schema version `4`
catalog state.
- For fixed-path destinations, the bounded destination bundle path is the
configured backend root. Dry-run output must make that clear.
- Preserve default behavior without `--force`:
- unmanaged planned path collisions fail as `fail_unmanaged`;
- invalid or future state fails as `fail_conflict`;
- no-state non-empty destinations fail as unmanaged.
- Ensure `force_replace` state creation uses the same catalog output projection
as normal publish planning.
- Keep `Force` out of config. There must be no persistent force default.
- Remove or update skipped force tests that were disabled during catalog
implementation.
Current-behavior documentation updates:
- Update only the force-related sections of:
- `docs/cli.md`;
- `docs/operations.md`;
- `docs/troubleshooting.md`;
- `docs/internal/publish.md`;
- backend integration docs where they describe forced deletion boundaries.
- Document force as an exceptional catalog recovery/replacement workflow, not as
a normal way to handle valid managed catalog state.
Tests:
- `go test ./internal/publish`
- `go test ./internal/app ./internal/cli`
- `go test ./internal/adapters/local ./internal/storage ./internal/storage/fake`
- Planning tests:
- no-state non-empty destination returns `fail_unmanaged` without force and
`force_replace` with force;
- unmanaged planned path collision returns `fail_unmanaged` without force and
`force_replace` with force;
- invalid state returns `fail_conflict` without force and `force_replace` with
force;
- future schema returns `fail_conflict` without force and `force_replace` with
force;
- valid catalog additive and replacement actions do not become
`force_replace`.
- Execution tests:
- `force_replace` clears only the destination bundle path;
- sibling paths outside the bundle path survive for local, fake S3, and fake
SSH-style backends;
- fixed-path force clears the configured backend root and is reported as such;
- resulting state is schema version `4` catalog state.
- CLI/app tests:
- dry-run `--force` reports `force_replace` without writing;
- normal `--force` executes and increments only the `force_replace` counter;
- JSON output includes stable `force_replace` action and summary fields.
Completion criteria:
- `run --force` has observable, tested catalog behavior.
- Force is still unnecessary for normal managed catalog replacement/upsert.
- Unmanaged/invalid/future-state replacement remains impossible without explicit
`--force`.
## Stage 2: Current Documentation And Example Synchronization
Goal: make all current-behavior docs and copyable examples match catalog schema
version `4` and the `workflow` config model.
Implementation scope:
- Rewrite `docs/config.md` so destination behavior is described through:
- `workflow: additive`;
- `workflow: replacement`;
- `publish`;
- `transform`;
- `path_mapping`;
- `links`;
- `retention`.
- Remove current-behavior documentation for destination config fields:
- `state`;
- `reconciliation`;
- `takeover`;
- `transfer`.
- Rewrite `docs/integrations/destination-state.md` around schema version `4`
catalog state:
- top-level catalog fields;
- output record fields;
- source identity fields;
- generated-output-only `source_path` and `transform`;
- optional per-output `url`;
- superseded legacy schema handling for publish planning.
- Update `docs/operations.md`:
- additive workflow semantics;
- replacement workflow semantics;
- catalog `force_replace`;
- prune and reconcile-state catalog behavior;
- dry-run action labels.
- Update `docs/troubleshooting.md`:
- replace legacy conflict guidance with workflow/catalog guidance;
- describe rejected legacy config fields;
- describe force-only exceptional cases.
- Update `docs/cli.md`:
- run summary counters now use `publish_new`, `upsert_additive`,
`replace_catalog`, `skip_same`, `force_replace`, `fail_unmanaged`, and
`fail_conflict`;
- remove legacy action labels from current command reference.
- Update relevant internal docs:
- `docs/internal/app.md`;
- `docs/internal/config.md`;
- `docs/internal/publish.md`;
- `docs/internal/state.md`.
- Update policy docs where current architectural text still describes
single-owner/shared-root behavior as current:
- `docs/policy/architecture.md`;
- `docs/policy/development.md`.
- Update examples:
- remove or rewrite `examples/shared-root.yml`;
- remove or rewrite `examples/merge-reconciliation.yml`;
- ensure examples use `workflow` where workflow intent matters;
- keep examples valid, secret-free, and copyable.
- Do not document any future catalog selectors, state migration, or compatibility
aliases outside `docs/roadmap/`.
Tests and checks:
- `go test ./internal/config ./internal/cli`
- `go test ./...`
- Run the config/example checks already used by the test suite.
- Manual smoke checks:
- `go run ./cmd/distributor run --config examples/local-publish.yml --dry-run`
- `go run ./cmd/distributor run --config examples/archive-and-latest.yml --dry-run`
- smoke any rewritten replacement/additive examples.
- Consistency searches:
- `rg -n "state:|reconciliation:|takeover:|transfer:" examples docs --glob '!docs/roadmap/**'`
- `rg -n "single_owner|shared_root|schema version \`2\`|schema version \`3\`" docs --glob '!docs/roadmap/**'`
- `rg -n "replace_older|replace_newer|replace_conflict|replace_takeover|takeover_mode" docs README.md examples --glob '!docs/roadmap/**'`
- `rg -n "workflow: additive|workflow: replacement|schema_version.*4" docs examples`
Completion criteria:
- Current docs describe implemented catalog behavior only.
- Copyable examples load successfully.
- No current doc tells users to configure rejected legacy fields.
- Destination state documentation is schema version `4` first.
## Stage 3: Catalog Idempotent Skip
Goal: make `skip_same` a real catalog no-op optimization instead of a stale
legacy action label.
Implementation scope:
- Implement `skip_same` when every planned output is already catalog-managed
with matching:
- pipeline id;
- destination id;
- source id;
- source digest;
- source created timestamp;
- output path;
- output kind;
- output digest;
- output size;
- generated output `source_path`;
- generated output `transform`;
- output URL metadata.
- Do not read destination bytes for this optimization. Trust valid catalog
metadata; bitrot detection remains a separate future concern.
- For `workflow: additive`, allow `skip_same` when all planned outputs match and
no planned output needs to be written. Unrelated catalog outputs are ignored
for the skip decision and remain retained.
- For `workflow: replacement`, allow `skip_same` only when all planned outputs
match and there are no current-owner catalog outputs that replacement workflow
would delete.
- Never return `skip_same` for superseded legacy state, invalid state, unmanaged
content, future state, or force replacement.
- `skip_same` must not write outputs, rewrite state, delete files, or notify.
- Count `skip_same` in text and JSON summaries.
- Keep behavior deterministic and identical across local, SSH, and S3
destinations.
Current-behavior documentation updates:
- Update `docs/cli.md`, `docs/operations.md`, and `docs/internal/publish.md` to
describe catalog `skip_same`.
- Document that `skip_same` is metadata-based and does not validate destination
bytes.
Tests:
- `go test ./internal/publish ./internal/app ./internal/cli`
- Repeated additive publish with identical catalog metadata returns
`skip_same`.
- Repeated replacement publish with identical catalog metadata and no omitted
current-owner outputs returns `skip_same`.
- Changed source digest, output digest, URL, transform mode, owner, output size,
or generated source path prevents skip.
- Replacement workflow does not skip when it would delete omitted current-owner
outputs.
- `skip_same` does not write outputs or state and does not notify.
- `go test ./...`
Completion criteria:
- Catalog action vocabulary has no stale action label.
- Repeated publish behavior is intentional, documented, and tested.
## Stage 4: Legacy Publish And State Code Removal
Goal: remove dead or near-dead single-owner/shared-root write and planning code
after catalog force behavior, docs, and skip semantics are settled.
Implementation scope:
- Remove legacy publish actions that are no longer planned or documented:
- `replace_older`;
- `replace_newer`;
- `replace_conflict`;
- `replace_takeover`;
- `skip_destination_newer`.
- Keep only catalog-era actions:
- `publish_new`;
- `upsert_additive`;
- `replace_catalog`;
- `skip_same`;
- `force_replace`;
- `fail_unmanaged`;
- `fail_conflict`.
- Remove legacy fields from `publish.Plan`:
- `StateMode`;
- `Reconciliation`;
- `TakeoverMode`;
- `ExistingState`;
- `ExistingSharedRoot`;
- shared-root owner/output carry fields retained only for old execution.
- Remove single-owner and shared-root execution branches from
`internal/publish/execute.go`.
- Remove unused single-owner/shared-root helper functions from `internal/publish`
once no tests or callers use them.
- Remove legacy destination config internals from `internal/config`:
- `StatePolicy`;
- `ReconciliationPolicy`;
- `TakeoverPolicy`;
- `TransferPolicy`;
- legacy constants and defaults that are no longer referenced.
- In `internal/state`, keep only what is needed for:
- parsing schema version `4` catalog state;
- identifying schema versions `1`, `2`, and `3` as superseded legacy by
schema number;
- validating and writing catalog state;
- pruning and reconciling catalog outputs.
- Delete or rewrite tests that assert legacy state parsing, validation,
comparison, shared-root ownership, or single-owner output behavior.
- Preserve test fixtures only where they are used to create superseded legacy
state for first catalog-run behavior. Prefer small local helpers over keeping
broad legacy state builders.
- Remove stale skipped tests that only represent old behavior. If a skipped test
still represents current expected behavior, unskip and update it.
Current-behavior documentation updates:
- No new user docs should be needed if Stage 2 is complete.
- Update internal docs only if removal changes internal package contracts beyond
what Stage 2 already documented.
Tests:
- `go test ./internal/state`
- `go test ./internal/publish`
- `go test ./internal/app ./internal/cli`
- `go test ./internal/config`
- `go test ./...`
- Consistency searches:
- `rg -n "ActionReplaceOlder|ActionReplaceNewer|ActionReplaceConflict|ActionReplaceTakeover|ActionSkipDestinationNewer" internal`
- `rg -n "StateModeSingleOwner|StateModeSharedRoot|SharedRootState|DistributorState|ParseSharedRoot|ReconciliationPolicy|TakeoverPolicy|TransferPolicy" internal --glob '!**/*_test.go'`
- `rg -n "Retained while the executor is migrated to catalog state" internal`
Completion criteria:
- Production publish execution has one catalog code path plus explicit
`force_replace`.
- Legacy config policy types are gone from production config structs/defaults.
- State package no longer exposes full v2/v3 implementation machinery unless it
is required by tests that generate superseded legacy fixtures.
- Full test suite passes without skipped tests that mask catalog cleanup work.
## Stage 5: Roadmap Closeout
Goal: leave `docs/roadmap/` in a clean state after the follow-up work is
implemented.
Implementation scope:
- Remove or rewrite completed roadmap material:
- this `implementation.md`;
- `docs/roadmap/catalog.md`, if catalog behavior is fully documented in
current docs;
- any future roadmap entries that still describe completed catalog cleanup as
pending work.
- Keep only genuinely future work in `docs/roadmap/future.md` or another active
roadmap file.
- Ensure future work remains out of current behavior docs.
Tests and checks:
- `go test ./...`
- `git status --short`
- `rg -n "future catalog|planned catalog|single_owner|shared_root|takeover|reconciliation|transfer" docs README.md examples`
- `rg -n "workflow: additive|workflow: replacement|schema_version.*4" docs README.md examples`
Completion criteria:
- Current docs, examples, and code describe the same implemented behavior.
- Roadmap docs contain only future work.
- Full test suite passes.
## Refactors To Avoid
- Do not reintroduce `state`, `reconciliation`, `takeover`, or `transfer` YAML
fields as deprecated aliases.
- Do not migrate legacy destination state into catalog state.
- Do not add top-level `owners` or `sources` to catalog state.
- Do not persist `workflow` in `.distributor.json`.
- Do not add new prune/reconcile selectors as part of this cleanup.
- Do not move catalog or force policy into storage adapters.
- Do not redesign the run JSON envelope while cleaning action labels.
## Open Questions
No open questions remain. This roadmap locks the follow-up decisions:
catalog `--force` will be implemented for exceptional destructive replacement,
current docs and examples will be synchronized to catalog schema version `4`,
catalog `skip_same` will be implemented as a metadata-only no-op optimization,
and legacy single-owner/shared-root implementation debt will be removed after
the catalog action vocabulary is complete.

View File

@@ -205,7 +205,7 @@ Reference: [Operations](operations.md#forced-replacement-workflow).
Symptom: `fail_conflict`, `destination source id differs`, `same id and created time but different digest`, `pipeline id ... does not match`, or `destination id ... does not match`.
Likely cause: `.distributor.json` belongs to a different pipeline, destination, source id, or same-created source with different content.
Likely cause: `.distributor.json` belongs to a different pipeline, destination, source id, shared-root output owner, or same-created source with different content. Valid managed identity, source, and shared-root output-owner mismatches can publish as `replace_takeover` when destination `takeover.mode` allows them, or as `replace_conflict` when `transfer.on_conflict: replace` allows managed conflict replacement.
Diagnostic:
@@ -214,7 +214,7 @@ cat <destination-path>/.distributor.json
go run ./cmd/distributor inspect <source-root>
```
Safe fix: verify the source and destination are intended to match. Use a separate destination path for unrelated content. To replace the existing state, configure `transfer.on_conflict: replace`, preview with `--dry-run --force`, then publish with `--force`.
Safe fix: verify the source and destination are intended to match. Use a separate destination path for unrelated content. For normal managed replacement, configure destination `takeover.mode` to match the intended ownership boundary or configure `transfer.on_conflict: replace`, then preview with `--dry-run`. Use `--force` only for exceptional replacement of unmanaged content or other force-only cases reported as `force_replace`.
Reference: [Operations](operations.md#destination-state-and-retry-behavior).
@@ -262,7 +262,7 @@ Reference: [Operations](operations.md#managed-output-pruning).
## Destination Is Newer Than Source
Symptom: `skip_destination_newer` or `destination is newer and replacement requires --force`.
Symptom: `skip_destination_newer`.
Likely cause: the destination state records a source manifest with a later `created` timestamp than the current source.
@@ -272,7 +272,7 @@ Diagnostic:
go run ./cmd/distributor run --config <config-path> --dry-run --format json
```
Safe fix: keep the default skip behavior unless replacement is intentional. To replace newer state, configure `transfer.on_destination_newer: replace`, preview with `--dry-run --force`, then publish with `--force`.
Safe fix: keep the default skip behavior unless replacement is intentional. To replace newer valid managed state, configure `transfer.on_destination_newer: replace`, preview with `--dry-run`, then publish without `--force`.
Reference: [Operations](operations.md#forced-replacement-workflow).
@@ -312,7 +312,7 @@ Reference: [Configuration](config.md#publish-and-transform-policy).
Symptom: `fail_conflict` with a reason like `destination output path ... is owned by <pipeline>/<destination>`.
Likely cause: a `state.mode: shared_root` destination planned an output path already recorded in `.distributor.json` for another pipeline/destination owner.
Likely cause: a `state.mode: shared_root` destination planned an output path already recorded in `.distributor.json` for another pipeline/destination owner, and `takeover.mode` does not allow that managed path to move to the current owner.
Diagnostic:
@@ -354,7 +354,7 @@ Diagnostic:
find <destination-path> -maxdepth 2 -print
```
Safe fix: inspect the destination bundle path printed in the error. `distributor` attempts to remove outputs from the failed attempt, but operators should verify the destination before retrying. In merge mode, previously managed retained or overwritten outputs may remain intentionally. Rerun `--dry-run` before publishing again.
Safe fix: inspect the destination bundle path printed in the error. `distributor` attempts to remove outputs from the failed attempt, but operators should verify the destination before retrying. In same-source merge mode, previously managed retained or overwritten outputs may remain intentionally. Rerun `--dry-run` before publishing again.
Reference: [Operations](operations.md#destination-state-and-retry-behavior).

View File

@@ -170,7 +170,7 @@ func (b *Backend) WriteFrom(ctx context.Context, logicalPath string, r io.Reader
return storage.Entry{}, storage.NewError(storage.OpWriteFrom, BackendName, logicalPath, storage.ErrConflict, fmt.Errorf("stream size %d does not match expected size %d", written, opts.Size))
}
if opts.PreferAtomic {
if err := b.client.Rename(writePath, nativePath); err != nil {
if err := renamePromotedFile(b.client, writePath, nativePath, opts.Overwrite); err != nil {
return storage.Entry{}, b.translateError(storage.OpWriteFrom, logicalPath, err)
}
cleanup = false
@@ -178,6 +178,27 @@ func (b *Backend) WriteFrom(ctx context.Context, logicalPath string, r io.Reader
return b.Stat(ctx, logicalPath)
}
type sftpRenamer interface {
PosixRename(oldname, newname string) error
Rename(oldname, newname string) error
Remove(path string) error
}
func renamePromotedFile(client sftpRenamer, oldname, newname string, overwrite bool) error {
if !overwrite {
return client.Rename(oldname, newname)
}
if err := client.PosixRename(oldname, newname); err == nil {
return nil
} else if !isReplaceRenameFallbackError(err) {
return err
}
if err := client.Remove(newname); err != nil && !isNotExist(err) {
return err
}
return client.Rename(oldname, newname)
}
func (b *Backend) Stat(ctx context.Context, logicalPath string) (storage.Entry, error) {
if err := ctx.Err(); err != nil {
return storage.Entry{}, err
@@ -464,6 +485,14 @@ func isNotExist(err error) bool {
return errors.Is(err, fs.ErrNotExist) || errors.Is(err, os.ErrNotExist) || errors.Is(err, sftp.ErrSSHFxNoSuchFile)
}
func isReplaceRenameFallbackError(err error) bool {
if errors.Is(err, sftp.ErrSSHFxFailure) || errors.Is(err, sftp.ErrSSHFxOpUnsupported) {
return true
}
var statusErr *sftp.StatusError
return errors.As(err, &statusErr) && (statusErr.FxCode() == sftp.ErrSSHFxFailure || statusErr.FxCode() == sftp.ErrSSHFxOpUnsupported)
}
func (b *Backend) translateError(op, logicalPath string, err error) error {
kind := storage.ErrUnknown
switch {

View File

@@ -0,0 +1,125 @@
package ssh
import (
"errors"
"os"
"testing"
"github.com/pkg/sftp"
)
func TestRenamePromotedFileUsesPlainRenameWithoutOverwrite(t *testing.T) {
client := &recordingRenamer{}
if err := renamePromotedFile(client, "temp", "index.html", false); err != nil {
t.Fatalf("renamePromotedFile() error = %v", err)
}
if got, want := client.calls, []string{"rename temp index.html"}; !equalStrings(got, want) {
t.Fatalf("calls = %q, want %q", got, want)
}
}
func TestRenamePromotedFileUsesPosixRenameForOverwrite(t *testing.T) {
client := &recordingRenamer{}
if err := renamePromotedFile(client, "temp", "index.html", true); err != nil {
t.Fatalf("renamePromotedFile() error = %v", err)
}
if got, want := client.calls, []string{"posix temp index.html"}; !equalStrings(got, want) {
t.Fatalf("calls = %q, want %q", got, want)
}
}
func TestRenamePromotedFileFallsBackWhenReplaceRenameUnsupported(t *testing.T) {
for _, err := range []error{
sftp.ErrSSHFxOpUnsupported,
sftp.ErrSSHFxFailure,
&sftp.StatusError{Code: uint32(sftp.ErrSSHFxOpUnsupported)},
&sftp.StatusError{Code: uint32(sftp.ErrSSHFxFailure)},
} {
t.Run(err.Error(), func(t *testing.T) {
client := &recordingRenamer{posixErr: err}
if err := renamePromotedFile(client, "temp", "index.html", true); err != nil {
t.Fatalf("renamePromotedFile() error = %v", err)
}
want := []string{"posix temp index.html", "remove index.html", "rename temp index.html"}
if got := client.calls; !equalStrings(got, want) {
t.Fatalf("calls = %q, want %q", got, want)
}
})
}
}
func TestRenamePromotedFileIgnoresMissingTargetDuringFallback(t *testing.T) {
client := &recordingRenamer{
posixErr: sftp.ErrSSHFxOpUnsupported,
removeErr: &os.PathError{
Op: "remove",
Path: "index.html",
Err: os.ErrNotExist,
},
}
if err := renamePromotedFile(client, "temp", "index.html", true); err != nil {
t.Fatalf("renamePromotedFile() error = %v", err)
}
want := []string{"posix temp index.html", "remove index.html", "rename temp index.html"}
if got := client.calls; !equalStrings(got, want) {
t.Fatalf("calls = %q, want %q", got, want)
}
}
func TestRenamePromotedFileDoesNotFallbackForPermissionError(t *testing.T) {
client := &recordingRenamer{posixErr: sftp.ErrSSHFxPermissionDenied}
if err := renamePromotedFile(client, "temp", "index.html", true); !errors.Is(err, sftp.ErrSSHFxPermissionDenied) {
t.Fatalf("renamePromotedFile() error = %v, want permission denied", err)
}
if got, want := client.calls, []string{"posix temp index.html"}; !equalStrings(got, want) {
t.Fatalf("calls = %q, want %q", got, want)
}
}
func TestRenamePromotedFileReturnsRemoveFallbackError(t *testing.T) {
client := &recordingRenamer{
posixErr: sftp.ErrSSHFxOpUnsupported,
removeErr: sftp.ErrSSHFxPermissionDenied,
}
if err := renamePromotedFile(client, "temp", "index.html", true); !errors.Is(err, sftp.ErrSSHFxPermissionDenied) {
t.Fatalf("renamePromotedFile() error = %v, want permission denied", err)
}
want := []string{"posix temp index.html", "remove index.html"}
if got := client.calls; !equalStrings(got, want) {
t.Fatalf("calls = %q, want %q", got, want)
}
}
type recordingRenamer struct {
calls []string
posixErr error
renameErr error
removeErr error
}
func (r *recordingRenamer) PosixRename(oldname, newname string) error {
r.calls = append(r.calls, "posix "+oldname+" "+newname)
return r.posixErr
}
func (r *recordingRenamer) Rename(oldname, newname string) error {
r.calls = append(r.calls, "rename "+oldname+" "+newname)
return r.renameErr
}
func (r *recordingRenamer) Remove(path string) error {
r.calls = append(r.calls, "remove "+path)
return r.removeErr
}
func equalStrings(a, b []string) bool {
if len(a) != len(b) {
return false
}
for index := range a {
if a[index] != b[index] {
return false
}
}
return true
}

View File

@@ -211,29 +211,18 @@ func removePrunedStateRecords(ctx context.Context, backend storage.Backend, stat
if len(paths) == 0 {
return false, nil
}
if document.SingleOwner != nil {
next, changed := state.RemoveMissingOutputs(*document.SingleOwner, paths)
if document.Catalog != nil {
next, changed := state.RemoveMissingCatalogOwnerOutputs(*document.Catalog, scope, paths)
if !changed {
return false, nil
}
next.UpdatedAt = now
if err := state.Validate(next); err != nil {
if err := state.ValidateCatalog(next); err != nil {
return false, err
}
return true, writeRepairedState(ctx, backend, statePath, next)
}
if document.SharedRoot != nil {
next, changed := state.RemoveMissingSharedRootOwnerOutputs(*document.SharedRoot, scope, paths)
if !changed {
return false, nil
}
next.UpdatedAt = now
if err := state.ValidateSharedRoot(next); err != nil {
return false, err
}
return true, writeRepairedState(ctx, backend, statePath, next)
}
return false, fmt.Errorf("destination state document is empty")
return false, unsupportedStateDocumentError(document)
}
func PlanPrune(document state.StateDocument, policy config.PrunePolicy, options PrunePlanOptions) (PrunePlanReport, error) {
@@ -266,17 +255,20 @@ func PlanPrune(document state.StateDocument, policy config.PrunePolicy, options
}
func pruneCandidatesForDocument(document state.StateDocument, scope state.OwnerScope) ([]state.PruneCandidate, error) {
if document.SingleOwner != nil {
singleOwner := *document.SingleOwner
if singleOwner.PipelineID != scope.PipelineID || singleOwner.DestinationID != scope.DestinationID {
return nil, fmt.Errorf("state owner is %s/%s, not %s/%s", singleOwner.PipelineID, singleOwner.DestinationID, scope.PipelineID, scope.DestinationID)
if document.Catalog != nil {
return state.CatalogPruneCandidates(*document.Catalog, scope), nil
}
return state.SingleOwnerPruneCandidates(singleOwner), nil
return nil, unsupportedStateDocumentError(document)
}
func unsupportedStateDocumentError(document state.StateDocument) error {
if document.SupersededLegacy != nil {
return fmt.Errorf("destination state schema_version %d is superseded legacy state", document.SupersededLegacy.SchemaVersion)
}
if document.SharedRoot != nil {
return state.SharedRootPruneCandidates(*document.SharedRoot, scope), nil
if document.SingleOwner != nil || document.SharedRoot != nil {
return fmt.Errorf("legacy destination state is not supported by this command")
}
return nil, fmt.Errorf("destination state document is empty")
return fmt.Errorf("destination state document is empty")
}
func pruneOlderThan(policy config.PrunePolicy) *time.Duration {

View File

@@ -15,7 +15,7 @@ import (
)
func TestPlanPruneDisabledPolicy(t *testing.T) {
document := state.StateDocument{SingleOwner: &state.DistributorState{}}
document := state.StateDocument{Catalog: &state.CatalogState{}}
report, err := PlanPrune(document, config.PrunePolicy{}, PrunePlanOptions{
PipelineID: "reports",
DestinationID: "archive",
@@ -28,12 +28,12 @@ func TestPlanPruneDisabledPolicy(t *testing.T) {
}
}
func TestPlanPruneSingleOwnerOutputs(t *testing.T) {
func TestPlanPruneCatalogOutputs(t *testing.T) {
now := time.Date(2026, 6, 8, 12, 0, 0, 0, time.UTC)
olderThan := config.Duration(48 * time.Hour)
destinationState := pruneSingleOwnerState(now)
catalog := pruneCatalogState(now)
report, err := PlanPrune(state.StateDocument{SingleOwner: &destinationState}, config.PrunePolicy{
report, err := PlanPrune(state.StateDocument{Catalog: &catalog}, config.PrunePolicy{
Enabled: true,
OlderThan: &olderThan,
}, PrunePlanOptions{
@@ -52,12 +52,12 @@ func TestPlanPruneSingleOwnerOutputs(t *testing.T) {
}
}
func TestPlanPruneSharedRootCurrentOwnerOnly(t *testing.T) {
func TestPlanPruneCatalogCurrentOwnerOnly(t *testing.T) {
now := time.Date(2026, 6, 8, 12, 0, 0, 0, time.UTC)
keepLatest := 0
sharedRoot := pruneSharedRootState(now)
catalog := pruneCatalogState(now)
report, err := PlanPrune(state.StateDocument{SharedRoot: &sharedRoot}, config.PrunePolicy{
report, err := PlanPrune(state.StateDocument{Catalog: &catalog}, config.PrunePolicy{
Enabled: true,
KeepLatest: &keepLatest,
}, PrunePlanOptions{
@@ -68,10 +68,10 @@ func TestPlanPruneSharedRootCurrentOwnerOnly(t *testing.T) {
if err != nil {
t.Fatalf("PlanPrune() error = %v", err)
}
if got, want := report.CheckedCount, 1; got != want {
if got, want := report.CheckedCount, 2; got != want {
t.Fatalf("checked count = %d, want %d", got, want)
}
if got, want := pruneRecordPaths(report.PrunedOutputs), "archive.txt"; got != want {
if got, want := pruneRecordPaths(report.PrunedOutputs), "old.txt,fresh.txt"; got != want {
t.Fatalf("pruned = %q, want %q", got, want)
}
}
@@ -80,8 +80,8 @@ func TestPruneDryRunReportsPlannedDeletesWithoutDeletingOrRewritingState(t *test
now := time.Date(2026, 6, 8, 12, 0, 0, 0, time.UTC)
backend := fake.New()
cfg := pruneS3Config(t, pruneOlderThanPolicy(48*time.Hour))
original := pruneSingleOwnerState(now)
writeFakeSingleOwnerStateForPrune(t, backend, original)
original := pruneCatalogState(now)
writeFakeCatalogState(t, backend, original)
testutil.WriteFakeFile(t, backend, "unmanaged.txt", "keep")
report, err := pruneConfigWithBackendFactory(context.Background(), cfg, PruneOptions{
@@ -102,12 +102,12 @@ func TestPruneDryRunReportsPlannedDeletesWithoutDeletingOrRewritingState(t *test
testutil.AssertFakeFile(t, backend, "old.txt", "managed")
testutil.AssertFakeFile(t, backend, "fresh.txt", "managed")
testutil.AssertFakeFile(t, backend, "unmanaged.txt", "keep")
destinationState := readFakeSingleOwnerState(t, backend)
if got := strings.Join(state.ManagedOutputPaths(destinationState), ","); got != "old.txt,fresh.txt" {
catalog := readFakeCatalogState(t, backend)
if got := strings.Join(state.CatalogManagedOutputPaths(catalog), ","); got != "old.txt,fresh.txt,html.txt" {
t.Fatalf("state outputs = %q, want original outputs", got)
}
if !destinationState.UpdatedAt.Equal(original.UpdatedAt) {
t.Fatalf("state updated_at = %s, want original %s", destinationState.UpdatedAt, original.UpdatedAt)
if !catalog.UpdatedAt.Equal(original.UpdatedAt) {
t.Fatalf("state updated_at = %s, want original %s", catalog.UpdatedAt, original.UpdatedAt)
}
}
@@ -115,7 +115,7 @@ func TestPruneApplyDeletesOnlyManagedOutputsAndUpdatesState(t *testing.T) {
now := time.Date(2026, 6, 8, 12, 0, 0, 0, time.UTC)
backend := fake.New()
cfg := pruneS3Config(t, pruneOlderThanPolicy(48*time.Hour))
writeFakeSingleOwnerStateForPrune(t, backend, pruneSingleOwnerState(now))
writeFakeCatalogState(t, backend, pruneCatalogState(now))
testutil.WriteFakeFile(t, backend, "unmanaged.txt", "keep")
report, err := pruneConfigWithBackendFactory(context.Background(), cfg, PruneOptions{
@@ -134,14 +134,18 @@ func TestPruneApplyDeletesOnlyManagedOutputsAndUpdatesState(t *testing.T) {
}
testutil.AssertFakeMissing(t, backend, "old.txt")
testutil.AssertFakeFile(t, backend, "fresh.txt", "managed")
testutil.AssertFakeFile(t, backend, "html.txt", "managed")
testutil.AssertFakeFile(t, backend, "unmanaged.txt", "keep")
assertFakeStateExists(t, backend)
destinationState := readFakeSingleOwnerState(t, backend)
if got := strings.Join(state.ManagedOutputPaths(destinationState), ","); got != "fresh.txt" {
catalog := readFakeCatalogState(t, backend)
if got := strings.Join(state.CatalogManagedOutputPaths(catalog), ","); got != "fresh.txt,html.txt" {
t.Fatalf("state outputs = %q, want fresh.txt", got)
}
if !destinationState.UpdatedAt.Equal(now) {
t.Fatalf("state updated_at = %s, want %s", destinationState.UpdatedAt, now)
if catalog.SchemaVersion != state.CatalogSchemaVersion {
t.Fatalf("state schema_version = %d, want %d", catalog.SchemaVersion, state.CatalogSchemaVersion)
}
if !catalog.UpdatedAt.Equal(now) {
t.Fatalf("state updated_at = %s, want %s", catalog.UpdatedAt, now)
}
}
@@ -150,7 +154,7 @@ func TestPruneApplyPreservesStateForFailedDeletes(t *testing.T) {
backend := fake.New()
keepLatest := 0
cfg := pruneS3Config(t, config.PrunePolicy{Enabled: true, KeepLatest: &keepLatest})
writeFakeSingleOwnerStateForPrune(t, backend, pruneSingleOwnerState(now))
writeFakeCatalogState(t, backend, pruneCatalogState(now))
failingBackend := failingDeleteBackend{Backend: backend, failPath: "fresh.txt"}
report, err := pruneConfigWithBackendFactory(context.Background(), cfg, PruneOptions{
@@ -170,18 +174,17 @@ func TestPruneApplyPreservesStateForFailedDeletes(t *testing.T) {
testutil.AssertFakeMissing(t, backend, "old.txt")
testutil.AssertFakeFile(t, backend, "fresh.txt", "managed")
assertFakeStateExists(t, backend)
destinationState := readFakeSingleOwnerState(t, backend)
if got := strings.Join(state.ManagedOutputPaths(destinationState), ","); got != "fresh.txt" {
catalog := readFakeCatalogState(t, backend)
if got := strings.Join(state.CatalogManagedOutputPaths(catalog), ","); got != "fresh.txt,html.txt" {
t.Fatalf("state outputs = %q, want only failed output preserved", got)
}
}
func TestPruneSharedRootPreservesOtherOwnersWhenScopedToCurrentOwner(t *testing.T) {
func TestPrunePreservesOtherOwnersWhenScopedToCurrentOwner(t *testing.T) {
now := time.Date(2026, 6, 8, 12, 0, 0, 0, time.UTC)
backend := fake.New()
keepLatest := 0
cfg := pruneS3Config(t, config.PrunePolicy{Enabled: true, KeepLatest: &keepLatest})
writeFakeSharedRootStateForApp(t, backend, pruneSharedRootState(now))
cfg := pruneS3Config(t, pruneOlderThanPolicy(48*time.Hour))
writeFakeCatalogState(t, backend, pruneCatalogState(now))
testutil.WriteFakeFile(t, backend, "unmanaged.txt", "keep")
report, err := pruneConfigWithBackendFactory(context.Background(), cfg, PruneOptions{
@@ -192,93 +195,56 @@ func TestPruneSharedRootPreservesOtherOwnersWhenScopedToCurrentOwner(t *testing.
if err != nil {
t.Fatalf("pruneConfigWithBackendFactory() error = %v", err)
}
if got, want := pruneRecordPaths(report.DeletedOutputs), "archive.txt"; got != want {
if got, want := pruneRecordPaths(report.DeletedOutputs), "old.txt"; got != want {
t.Fatalf("deleted outputs = %q, want %q", got, want)
}
testutil.AssertFakeMissing(t, backend, "archive.txt")
testutil.AssertFakeFile(t, backend, "html.txt", "old")
testutil.AssertFakeMissing(t, backend, "old.txt")
testutil.AssertFakeFile(t, backend, "html.txt", "managed")
testutil.AssertFakeFile(t, backend, "unmanaged.txt", "keep")
sharedRoot := readFakeSharedRootStateForApp(t, backend)
if got := strings.Join(sharedRoot.AllManagedOutputPaths(), ","); got != "html.txt" {
t.Fatalf("shared-root outputs = %q, want other owner output preserved", got)
catalog := readFakeCatalogState(t, backend)
if got := strings.Join(state.CatalogManagedOutputPaths(catalog), ","); got != "fresh.txt,html.txt" {
t.Fatalf("catalog outputs = %q, want other owner output preserved", got)
}
}
func pruneSingleOwnerState(now time.Time) state.DistributorState {
func pruneCatalogState(now time.Time) state.CatalogState {
manifest := testutil.ValidManifest(testutil.BundleOptions{})
publishedAt := now.Add(-96 * time.Hour)
return state.DistributorState{
SchemaVersion: state.SchemaVersion,
createdAt := now.Add(-96 * time.Hour)
source := state.CatalogSourceIdentity{ID: manifest.ID, Digest: manifest.Digest, Created: manifest.Created}
return state.CatalogState{
SchemaVersion: state.CatalogSchemaVersion,
DistributorVersion: "test",
CreatedAt: createdAt,
UpdatedAt: createdAt,
State: state.StatePolicy{Mode: state.StateModeCatalog},
Outputs: []state.CatalogOutputFile{{
Path: "old.txt",
PipelineID: "reports",
DestinationID: "archive",
PublishedAt: publishedAt,
CreatedAt: publishedAt,
UpdatedAt: publishedAt,
State: state.StatePolicy{Mode: state.StateModeSingleOwner},
Reconciliation: state.ReconciliationPolicy{Mode: config.ReconciliationModeReplace},
Source: state.SourceState{Manifest: manifest},
DistributorVersion: "test",
Outputs: []state.OutputFile{{
Path: "old.txt",
Source: source,
Kind: state.OutputKindSource,
SourcePath: "report.md",
SHA256: manifest.Files[0].SHA256,
Size: manifest.Files[0].Size,
CreatedAt: now.Add(-96 * time.Hour),
UpdatedAt: now.Add(-72 * time.Hour),
}, {
Path: "fresh.txt",
PipelineID: "reports",
DestinationID: "archive",
Source: source,
Kind: state.OutputKindSource,
SourcePath: "summary.txt",
SHA256: manifest.Files[1].SHA256,
Size: manifest.Files[1].Size,
CreatedAt: now.Add(-24 * time.Hour),
UpdatedAt: now.Add(-24 * time.Hour),
}},
}
}
func pruneSharedRootState(now time.Time) state.SharedRootState {
manifest := testutil.ValidManifest(testutil.BundleOptions{})
archive := state.CurrentOwnerScope("reports", "archive")
html := state.CurrentOwnerScope("reports", "html")
return state.SharedRootState{
SchemaVersion: state.SharedRootSchemaVersion,
DistributorVersion: "test",
CreatedAt: now.Add(-96 * time.Hour),
UpdatedAt: now.Add(-24 * time.Hour),
State: state.StatePolicy{Mode: state.StateModeSharedRoot},
Owners: []state.OwnerRecord{{
Scope: archive,
Reconciliation: state.ReconciliationPolicy{Mode: config.ReconciliationModeReplace},
Source: state.SourceState{Manifest: manifest},
}, {
Scope: html,
Reconciliation: state.ReconciliationPolicy{Mode: config.ReconciliationModeReplace},
Source: state.SourceState{Manifest: manifest},
}},
Outputs: []state.SharedRootOutputFile{{
Path: "archive.txt",
Kind: state.OutputKindSource,
SourcePath: "report.md",
SHA256: manifest.Files[0].SHA256,
Size: manifest.Files[0].Size,
Owner: archive,
SourceID: manifest.ID,
SourceDigest: manifest.Digest,
SourceCreated: manifest.Created,
CreatedAt: now.Add(-96 * time.Hour),
UpdatedAt: now.Add(-72 * time.Hour),
CreatedAt: now.Add(-24 * time.Hour),
UpdatedAt: now.Add(-24 * time.Hour),
}, {
Path: "html.txt",
PipelineID: "reports",
DestinationID: "html",
Source: source,
Kind: state.OutputKindSource,
SourcePath: "summary.txt",
SHA256: manifest.Files[1].SHA256,
Size: manifest.Files[1].Size,
Owner: html,
SourceID: manifest.ID,
SourceDigest: manifest.Digest,
SourceCreated: manifest.Created,
CreatedAt: now.Add(-96 * time.Hour),
UpdatedAt: now.Add(-72 * time.Hour),
}},
@@ -319,18 +285,31 @@ func pruneOlderThanPolicy(duration time.Duration) config.PrunePolicy {
}
}
func writeFakeSingleOwnerStateForPrune(t *testing.T, backend *fake.Backend, destinationState state.DistributorState) {
func writeFakeCatalogState(t *testing.T, backend *fake.Backend, catalog state.CatalogState) {
t.Helper()
data, err := json.MarshalIndent(destinationState, "", " ")
data, err := json.MarshalIndent(catalog, "", " ")
if err != nil {
t.Fatalf("marshal single-owner state: %v", err)
t.Fatalf("marshal catalog state: %v", err)
}
testutil.WriteFakeFile(t, backend, storage.StateFileName, string(append(data, '\n')))
for _, output := range destinationState.Outputs {
for _, output := range catalog.Outputs {
testutil.WriteFakeFile(t, backend, output.Path, "managed")
}
}
func readFakeCatalogState(t *testing.T, backend *fake.Backend) state.CatalogState {
t.Helper()
data, err := backend.ReadFile(context.Background(), storage.StateFileName)
if err != nil {
t.Fatalf("read catalog state: %v", err)
}
catalog, err := state.ParseCatalog(data)
if err != nil {
t.Fatalf("parse catalog state: %v", err)
}
return catalog
}
func assertFakeStateExists(t *testing.T, backend *fake.Backend) {
t.Helper()
if _, err := backend.Stat(context.Background(), storage.StateFileName); err != nil {

View File

@@ -158,62 +158,25 @@ func buildReconcileStateReport(ctx context.Context, backend storage.Backend, pip
DryRun: options.DryRun,
}
scope := state.CurrentOwnerScope(pipeline.ID, destination.ID)
if document.SingleOwner != nil {
return reconcileSingleOwnerState(ctx, backend, statePath, *document.SingleOwner, scope, report, options)
if document.Catalog != nil {
return reconcileCatalogState(ctx, backend, statePath, *document.Catalog, scope, report, options)
}
return reconcileSharedRootState(ctx, backend, statePath, *document.SharedRoot, scope, report, options)
return ReconcileStateReport{}, unsupportedStateDocumentError(document)
}
func reconcileSingleOwnerState(ctx context.Context, backend storage.Backend, statePath string, destinationState state.DistributorState, scope state.OwnerScope, report ReconcileStateReport, options ReconcileStateOptions) (ReconcileStateReport, error) {
if destinationState.PipelineID != scope.PipelineID || destinationState.DestinationID != scope.DestinationID {
return ReconcileStateReport{}, fmt.Errorf("state owner is %s/%s, not %s/%s", destinationState.PipelineID, destinationState.DestinationID, scope.PipelineID, scope.DestinationID)
}
report.StateSchema = destinationState.SchemaVersion
report.OwnerScope = &ReconcileStateOwnerScope{PipelineID: scope.PipelineID, DestinationID: scope.DestinationID}
managed := state.ManagedOutputPaths(destinationState)
missing, err := missingSingleOwnerOutputs(ctx, backend, destinationState.Outputs)
if err != nil {
return ReconcileStateReport{}, err
}
report.CheckedCount = len(managed)
report.MissingManagedOutputs = missing
unmanaged, err := unmanagedEntries(ctx, backend, managed)
if err != nil {
return ReconcileStateReport{}, err
}
report.UnmanagedEntries = unmanaged
report.WouldChange = options.DryRun && len(missing) > 0
if !options.DryRun && len(missing) > 0 {
missingPaths := missingReportPaths(missing)
next, changed := state.RemoveMissingOutputs(destinationState, missingPaths)
report.Changed = changed
if changed {
next.UpdatedAt = time.Now().UTC()
if err := state.Validate(next); err != nil {
return ReconcileStateReport{}, err
}
if err := writeRepairedState(ctx, backend, statePath, next); err != nil {
return ReconcileStateReport{}, err
}
}
}
return report, nil
}
func reconcileSharedRootState(ctx context.Context, backend storage.Backend, statePath string, sharedRoot state.SharedRootState, scope state.OwnerScope, report ReconcileStateReport, options ReconcileStateOptions) (ReconcileStateReport, error) {
report.StateSchema = sharedRoot.SchemaVersion
func reconcileCatalogState(ctx context.Context, backend storage.Backend, statePath string, catalog state.CatalogState, scope state.OwnerScope, report ReconcileStateReport, options ReconcileStateOptions) (ReconcileStateReport, error) {
report.StateSchema = catalog.SchemaVersion
report.OwnerScope = &ReconcileStateOwnerScope{
PipelineID: scope.PipelineID,
DestinationID: scope.DestinationID,
AllOwners: options.AllOwners,
}
managed := sharedRoot.AllManagedOutputPaths()
outputs := sharedRoot.Outputs
managed := state.CatalogManagedOutputPaths(catalog)
outputs := catalog.Outputs
if !options.AllOwners {
outputs = sharedRootOutputsForOwner(sharedRoot.Outputs, scope)
outputs = state.CatalogOutputsForOwner(catalog.Outputs, scope)
}
missing, err := missingSharedRootOutputs(ctx, backend, outputs)
missing, err := missingCatalogOutputs(ctx, backend, outputs)
if err != nil {
return ReconcileStateReport{}, err
}
@@ -228,17 +191,17 @@ func reconcileSharedRootState(ctx context.Context, backend storage.Backend, stat
if !options.DryRun && len(missing) > 0 {
missingPaths := missingReportPaths(missing)
var next state.SharedRootState
var next state.CatalogState
var changed bool
if options.AllOwners {
next, changed = state.RemoveMissingSharedRootOutputs(sharedRoot, missingPaths)
next, changed = state.RemoveMissingCatalogOutputs(catalog, missingPaths)
} else {
next, changed = state.RemoveMissingSharedRootOwnerOutputs(sharedRoot, scope, missingPaths)
next, changed = state.RemoveMissingCatalogOwnerOutputs(catalog, scope, missingPaths)
}
report.Changed = changed
if changed {
next.UpdatedAt = time.Now().UTC()
if err := state.ValidateSharedRoot(next); err != nil {
if err := state.ValidateCatalog(next); err != nil {
return ReconcileStateReport{}, err
}
if err := writeRepairedState(ctx, backend, statePath, next); err != nil {
@@ -249,21 +212,7 @@ func reconcileSharedRootState(ctx context.Context, backend storage.Backend, stat
return report, nil
}
func missingSingleOwnerOutputs(ctx context.Context, backend storage.Backend, outputs []state.OutputFile) ([]ReconcileStatePath, error) {
missing := make([]ReconcileStatePath, 0)
for _, output := range outputs {
if err := checkManagedOutput(ctx, backend, output.Path); err != nil {
if storage.IsNotFound(err) {
missing = append(missing, ReconcileStatePath{Path: output.Path, StorageStatus: "missing"})
continue
}
return nil, err
}
}
return missing, nil
}
func missingSharedRootOutputs(ctx context.Context, backend storage.Backend, outputs []state.SharedRootOutputFile) ([]ReconcileStatePath, error) {
func missingCatalogOutputs(ctx context.Context, backend storage.Backend, outputs []state.CatalogOutputFile) ([]ReconcileStatePath, error) {
missing := make([]ReconcileStatePath, 0)
for _, output := range outputs {
if err := checkManagedOutput(ctx, backend, output.Path); err != nil {
@@ -271,8 +220,8 @@ func missingSharedRootOutputs(ctx context.Context, backend storage.Backend, outp
missing = append(missing, ReconcileStatePath{
Path: output.Path,
OwnerScope: &ReconcileStateOwnerScope{
PipelineID: output.Owner.PipelineID,
DestinationID: output.Owner.DestinationID,
PipelineID: output.PipelineID,
DestinationID: output.DestinationID,
},
StorageStatus: "missing",
})
@@ -320,16 +269,6 @@ func unmanagedEntries(ctx context.Context, backend storage.Backend, managedPaths
return entries, nil
}
func sharedRootOutputsForOwner(outputs []state.SharedRootOutputFile, scope state.OwnerScope) []state.SharedRootOutputFile {
selected := make([]state.SharedRootOutputFile, 0, len(outputs))
for _, output := range outputs {
if output.Owner == scope {
selected = append(selected, output)
}
}
return selected
}
func missingReportPaths(missing []ReconcileStatePath) []string {
paths := make([]string, 0, len(missing))
for _, item := range missing {

View File

@@ -2,7 +2,6 @@ package app
import (
"context"
"encoding/json"
"strings"
"testing"
"time"
@@ -17,9 +16,9 @@ import (
func TestReconcileStateDryRunReportsMissingManagedOutputsWithoutRewrite(t *testing.T) {
backend := fake.New()
cfg := reconcileStateS3Config(t)
manifest := testutil.ValidManifest(testutil.BundleOptions{})
testutil.WriteFakeDestinationState(t, backend, "", manifest, testutil.DestinationStateOptions{})
if err := backend.DeleteManagedOutputs(context.Background(), "", []string{"summary.txt"}, storage.DeleteOptions{}); err != nil {
catalog := pruneCatalogState(time.Date(2026, 6, 8, 12, 0, 0, 0, time.UTC))
writeFakeCatalogState(t, backend, catalog)
if err := backend.DeleteManagedOutputs(context.Background(), "", []string{"fresh.txt"}, storage.DeleteOptions{}); err != nil {
t.Fatalf("delete managed output: %v", err)
}
testutil.WriteFakeFile(t, backend, "extra.txt", "unmanaged")
@@ -35,14 +34,14 @@ func TestReconcileStateDryRunReportsMissingManagedOutputsWithoutRewrite(t *testi
if !report.WouldChange || report.Changed {
t.Fatalf("report changed=%t would_change=%t, want dry-run pending change", report.Changed, report.WouldChange)
}
if got := reportPathList(report.MissingManagedOutputs); got != "summary.txt" {
t.Fatalf("missing outputs = %q, want summary.txt", got)
if got := reportPathList(report.MissingManagedOutputs); got != "fresh.txt" {
t.Fatalf("missing outputs = %q, want fresh.txt", got)
}
if got := entryPathList(report.UnmanagedEntries); got != "extra.txt" {
t.Fatalf("unmanaged entries = %q, want extra.txt", got)
}
destinationState := readFakeSingleOwnerState(t, backend)
if got := strings.Join(state.ManagedOutputPaths(destinationState), ","); got != "report.md,summary.txt" {
repaired := readFakeCatalogState(t, backend)
if got := strings.Join(state.CatalogManagedOutputPaths(repaired), ","); got != "old.txt,fresh.txt,html.txt" {
t.Fatalf("state outputs = %q, want original outputs", got)
}
}
@@ -50,9 +49,8 @@ func TestReconcileStateDryRunReportsMissingManagedOutputsWithoutRewrite(t *testi
func TestReconcileStateApplyRemovesMissingRecordsAndPreservesUnmanagedFiles(t *testing.T) {
backend := fake.New()
cfg := reconcileStateS3Config(t)
manifest := testutil.ValidManifest(testutil.BundleOptions{})
testutil.WriteFakeDestinationState(t, backend, "", manifest, testutil.DestinationStateOptions{})
if err := backend.DeleteManagedOutputs(context.Background(), "", []string{"summary.txt"}, storage.DeleteOptions{}); err != nil {
writeFakeCatalogState(t, backend, pruneCatalogState(time.Date(2026, 6, 8, 12, 0, 0, 0, time.UTC)))
if err := backend.DeleteManagedOutputs(context.Background(), "", []string{"fresh.txt"}, storage.DeleteOptions{}); err != nil {
t.Fatalf("delete managed output: %v", err)
}
testutil.WriteFakeFile(t, backend, "extra.txt", "unmanaged")
@@ -67,12 +65,15 @@ func TestReconcileStateApplyRemovesMissingRecordsAndPreservesUnmanagedFiles(t *t
if !report.Changed || report.WouldChange {
t.Fatalf("report changed=%t would_change=%t, want applied change", report.Changed, report.WouldChange)
}
destinationState := readFakeSingleOwnerState(t, backend)
if err := state.Validate(destinationState); err != nil {
t.Fatalf("Validate() repaired state error = %v", err)
repaired := readFakeCatalogState(t, backend)
if err := state.ValidateCatalog(repaired); err != nil {
t.Fatalf("ValidateCatalog() repaired state error = %v", err)
}
if got := strings.Join(state.ManagedOutputPaths(destinationState), ","); got != "report.md" {
t.Fatalf("state outputs = %q, want report.md", got)
if got := strings.Join(state.CatalogManagedOutputPaths(repaired), ","); got != "old.txt,html.txt" {
t.Fatalf("state outputs = %q, want old.txt,html.txt", got)
}
if repaired.SchemaVersion != state.CatalogSchemaVersion {
t.Fatalf("state schema_version = %d, want %d", repaired.SchemaVersion, state.CatalogSchemaVersion)
}
testutil.AssertFakeFile(t, backend, "extra.txt", "unmanaged")
}
@@ -99,12 +100,11 @@ func TestReconcileStateInvalidStateFailsWithoutRewrite(t *testing.T) {
}
}
func TestReconcileStateSharedRootOwnerScopeRepairsCurrentOwnerOnly(t *testing.T) {
func TestReconcileStateOwnerScopeRepairsCurrentOwnerOnly(t *testing.T) {
backend := fake.New()
cfg := reconcileStateS3Config(t)
sharedRoot := reconcileSharedRootFixture(t)
writeFakeSharedRootStateForApp(t, backend, sharedRoot)
if err := backend.DeleteManagedOutputs(context.Background(), "", []string{"report.md", "report.html"}, storage.DeleteOptions{}); err != nil {
writeFakeCatalogState(t, backend, pruneCatalogState(time.Date(2026, 6, 8, 12, 0, 0, 0, time.UTC)))
if err := backend.DeleteManagedOutputs(context.Background(), "", []string{"old.txt", "html.txt"}, storage.DeleteOptions{}); err != nil {
t.Fatalf("delete managed outputs: %v", err)
}
@@ -118,18 +118,17 @@ func TestReconcileStateSharedRootOwnerScopeRepairsCurrentOwnerOnly(t *testing.T)
if !report.Changed {
t.Fatal("report changed = false, want true")
}
repaired := readFakeSharedRootStateForApp(t, backend)
if got := strings.Join(repaired.AllManagedOutputPaths(), ","); got != "report.html" {
t.Fatalf("shared-root outputs = %q, want other owner output preserved", got)
repaired := readFakeCatalogState(t, backend)
if got := strings.Join(state.CatalogManagedOutputPaths(repaired), ","); got != "fresh.txt,html.txt" {
t.Fatalf("catalog outputs = %q, want other owner output preserved", got)
}
}
func TestReconcileStateSharedRootAllOwnersRepairsEveryOwner(t *testing.T) {
func TestReconcileStateAllOwnersRepairsEveryOwner(t *testing.T) {
backend := fake.New()
cfg := reconcileStateS3Config(t)
sharedRoot := reconcileSharedRootFixture(t)
writeFakeSharedRootStateForApp(t, backend, sharedRoot)
if err := backend.DeleteManagedOutputs(context.Background(), "", []string{"report.md", "report.html"}, storage.DeleteOptions{}); err != nil {
writeFakeCatalogState(t, backend, pruneCatalogState(time.Date(2026, 6, 8, 12, 0, 0, 0, time.UTC)))
if err := backend.DeleteManagedOutputs(context.Background(), "", []string{"old.txt", "html.txt"}, storage.DeleteOptions{}); err != nil {
t.Fatalf("delete managed outputs: %v", err)
}
@@ -141,12 +140,12 @@ func TestReconcileStateSharedRootAllOwnersRepairsEveryOwner(t *testing.T) {
if err != nil {
t.Fatalf("reconcileStateConfigWithBackendFactory() error = %v", err)
}
if !report.Changed || report.CheckedCount != 2 {
if !report.Changed || report.CheckedCount != 3 {
t.Fatalf("report changed=%t checked=%d, want all-owner repair", report.Changed, report.CheckedCount)
}
repaired := readFakeSharedRootStateForApp(t, backend)
if got := repaired.AllManagedOutputPaths(); len(got) != 0 {
t.Fatalf("shared-root outputs = %#v, want none", got)
repaired := readFakeCatalogState(t, backend)
if got := strings.Join(state.CatalogManagedOutputPaths(repaired), ","); got != "fresh.txt" {
t.Fatalf("catalog outputs = %q, want fresh.txt", got)
}
}
@@ -165,93 +164,6 @@ func reconcileStateS3Config(t *testing.T) config.Config {
return cfg
}
func readFakeSingleOwnerState(t *testing.T, backend *fake.Backend) state.DistributorState {
t.Helper()
data, err := backend.ReadFile(context.Background(), storage.StateFileName)
if err != nil {
t.Fatalf("read state: %v", err)
}
destinationState, err := state.Parse(data)
if err != nil {
t.Fatalf("parse state: %v", err)
}
return destinationState
}
func writeFakeSharedRootStateForApp(t *testing.T, backend *fake.Backend, sharedRoot state.SharedRootState) {
t.Helper()
data, err := json.MarshalIndent(sharedRoot, "", " ")
if err != nil {
t.Fatalf("marshal shared-root state: %v", err)
}
testutil.WriteFakeFile(t, backend, storage.StateFileName, string(append(data, '\n')))
for _, output := range sharedRoot.Outputs {
testutil.WriteFakeFile(t, backend, output.Path, "old")
}
}
func readFakeSharedRootStateForApp(t *testing.T, backend *fake.Backend) state.SharedRootState {
t.Helper()
data, err := backend.ReadFile(context.Background(), storage.StateFileName)
if err != nil {
t.Fatalf("read shared-root state: %v", err)
}
sharedRoot, err := state.ParseSharedRoot(data)
if err != nil {
t.Fatalf("parse shared-root state: %v", err)
}
return sharedRoot
}
func reconcileSharedRootFixture(t *testing.T) state.SharedRootState {
t.Helper()
source := testutil.ValidManifest(testutil.BundleOptions{})
htmlSource := source
createdAt := time.Date(2026, 5, 30, 11, 12, 0, 0, time.UTC)
return state.SharedRootState{
SchemaVersion: state.SharedRootSchemaVersion,
DistributorVersion: "test",
CreatedAt: createdAt,
UpdatedAt: createdAt,
State: state.StatePolicy{Mode: state.StateModeSharedRoot},
Owners: []state.OwnerRecord{{
Scope: state.CurrentOwnerScope("reports", "archive"),
Reconciliation: state.ReconciliationPolicy{Mode: config.ReconciliationModeReplace},
Source: state.SourceState{Manifest: source},
}, {
Scope: state.CurrentOwnerScope("reports", "html"),
Reconciliation: state.ReconciliationPolicy{Mode: config.ReconciliationModeMerge},
Source: state.SourceState{Manifest: htmlSource},
}},
Outputs: []state.SharedRootOutputFile{{
Path: "report.md",
Kind: state.OutputKindSource,
SourcePath: "report.md",
SHA256: source.Files[0].SHA256,
Size: source.Files[0].Size,
Owner: state.CurrentOwnerScope("reports", "archive"),
SourceID: source.ID,
SourceDigest: source.Digest,
SourceCreated: source.Created,
CreatedAt: createdAt,
UpdatedAt: createdAt,
}, {
Path: "report.html",
Kind: state.OutputKindGenerated,
SourcePath: "report.md",
Transform: "markdown_to_html",
SHA256: "sha256:" + strings.Repeat("a", 64),
Size: 128,
Owner: state.CurrentOwnerScope("reports", "html"),
SourceID: htmlSource.ID,
SourceDigest: htmlSource.Digest,
SourceCreated: htmlSource.Created,
CreatedAt: createdAt,
UpdatedAt: createdAt,
}},
}
}
func reportPathList(paths []ReconcileStatePath) string {
values := make([]string, 0, len(paths))
for _, path := range paths {

View File

@@ -69,10 +69,8 @@ func processDestinationSelection(ctx context.Context, request runDestinationRequ
Publish: *request.destination.Publish,
Transform: request.destination.Transform,
Links: request.destination.Links,
State: request.destination.State,
Reconciliation: request.destination.Reconciliation,
Workflow: request.destination.Workflow,
Transformers: request.transforms,
Transfer: request.destination.Transfer,
DistributorVersion: Version,
Force: request.options.Force,
}
@@ -82,8 +80,8 @@ func processDestinationSelection(ctx context.Context, request runDestinationRequ
}
if isFixedPathDestination(request.destination) {
plan.PathMapping = config.PathMappingFixed
if request.options.DryRun && isDestructiveFixedPathAction(plan.Action) {
warning := fixedPathReplacementWarning(plan)
if request.options.DryRun && isFixedPathWorkflowAction(plan.Action) {
warning := fixedPathWorkflowWarning(plan)
request.recorder.addPipelineWarning(request.pipelineIndex, warning)
}
}
@@ -141,6 +139,7 @@ func (recorder *runReportRecorder) recordDestinationFailure(pipelineIndex int, f
recorder.failures.add(failure.pipelineID, failure.destinationID, failure.backend, storage.DisplayPath(failure.bundlePath), failure.err)
recorder.summary.recordFailure()
if includeAction {
recorder.summary.recordFailureAction(action.Action)
recorder.addPipelineAction(pipelineIndex, action)
}
}
@@ -161,5 +160,8 @@ func completePlanIdentity(plan publish.Plan, pipeline config.Pipeline, destinati
if plan.DestinationBundlePath == "" {
plan.DestinationBundlePath = selection.DestinationBundlePath
}
if plan.Workflow == "" {
plan.Workflow = destination.Workflow
}
return plan
}

View File

@@ -6,7 +6,7 @@ import (
)
func shouldNotify(action publish.Action) bool {
return action == publish.ActionPublishNew || action == publish.ActionReplaceOlder || action == publish.ActionForceReplace
return action == publish.ActionPublishNew || action == publish.ActionUpsertAdditive || action == publish.ActionReplaceCatalog || action == publish.ActionForceReplace
}
func notifyEvent(plan publish.Plan) notify.Event {

View File

@@ -60,7 +60,7 @@ func writeRunActionLine(w io.Writer, action RunActionRecord) {
fmt.Fprintf(w, " - bundle=%s destination=%s backend=%s%s action=error reason=%q\n", action.BundlePath, destinationID, action.Backend, pathMappingRecordSummary(action), action.Reason)
return
}
fmt.Fprintf(w, " - bundle=%s destination=%s backend=%s%s action=%s outputs=%s reason=%q\n", action.BundlePath, action.DestinationID, action.Backend, pathMappingRecordSummary(action), action.Action, outputRecordSummary(action.Outputs), action.Reason)
fmt.Fprintf(w, " - bundle=%s destination=%s backend=%s%s action=%s%s outputs=%s reason=%q\n", action.BundlePath, action.DestinationID, action.Backend, pathMappingRecordSummary(action), action.Action, workflowRecordSummary(action), outputRecordSummary(action.Outputs), action.Reason)
}
func pathMappingRecordSummary(action RunActionRecord) string {
@@ -70,6 +70,13 @@ func pathMappingRecordSummary(action RunActionRecord) string {
return fmt.Sprintf(" path_mapping=fixed target=%s", action.DestinationPath)
}
func workflowRecordSummary(action RunActionRecord) string {
if action.Workflow == "" {
return ""
}
return fmt.Sprintf(" workflow=%s", action.Workflow)
}
func outputRecordSummary(outputs []RunOutputRecord) string {
if len(outputs) == 0 {
return "none"
@@ -136,6 +143,7 @@ type RunActionRecord struct {
BundlePath string `json:"bundle_path"`
DestinationPath string `json:"destination_path"`
PathMapping string `json:"path_mapping,omitempty"`
Workflow string `json:"workflow,omitempty"`
Action string `json:"action"`
PrimaryURL string `json:"primary_url,omitempty"`
Reason string `json:"reason,omitempty"`
@@ -158,6 +166,13 @@ func runActionFromPlan(backend string, plan publish.Plan, planErr error) RunActi
if destinationID == "" {
destinationID = "unknown"
}
action := "error"
outputs := []RunOutputRecord{}
switch plan.Action {
case publish.ActionFailUnmanaged, publish.ActionFailConflict:
action = string(plan.Action)
outputs = runOutputsFromPlan(plan.Outputs)
}
return RunActionRecord{
PipelineID: plan.PipelineID,
DestinationID: destinationID,
@@ -166,10 +181,11 @@ func runActionFromPlan(backend string, plan publish.Plan, planErr error) RunActi
BundlePath: storage.DisplayPath(plan.BundlePath),
DestinationPath: storage.DisplayPath(plan.DestinationBundlePath),
PathMapping: plan.PathMapping,
Action: "error",
Workflow: plan.Workflow,
Action: action,
PrimaryURL: plan.PrimaryURL,
Reason: planErr.Error(),
Outputs: []RunOutputRecord{},
Outputs: outputs,
}
}
return RunActionRecord{
@@ -180,6 +196,7 @@ func runActionFromPlan(backend string, plan publish.Plan, planErr error) RunActi
BundlePath: storage.DisplayPath(plan.BundlePath),
DestinationPath: storage.DisplayPath(plan.DestinationBundlePath),
PathMapping: plan.PathMapping,
Workflow: plan.Workflow,
Action: string(plan.Action),
PrimaryURL: plan.PrimaryURL,
Reason: plan.Reason,

View File

@@ -62,12 +62,22 @@ func fixedPathSelectionWarning(pipelineID, destinationID string, selections []de
return OutputWarning{Message: fmt.Sprintf("pipeline=%s destination=%s path_mapping=fixed candidates=%d selected_bundle=%s destination_bundle=.", pipelineID, destinationID, candidateCount, selected)}
}
func isDestructiveFixedPathAction(action publish.Action) bool {
return action == publish.ActionReplaceOlder || action == publish.ActionForceReplace
func isFixedPathWorkflowAction(action publish.Action) bool {
return action == publish.ActionUpsertAdditive || action == publish.ActionReplaceCatalog || action == publish.ActionForceReplace
}
func fixedPathReplacementWarning(plan publish.Plan) OutputWarning {
return OutputWarning{Message: fmt.Sprintf("pipeline=%s destination=%s path_mapping=fixed action=%s replaces destination root for selected_bundle=%s", plan.PipelineID, plan.DestinationID, plan.Action, storage.DisplayPath(plan.BundlePath))}
func fixedPathWorkflowWarning(plan publish.Plan) OutputWarning {
switch plan.Action {
case publish.ActionReplaceCatalog:
if plan.ClearDestinationRoot {
return OutputWarning{Message: fmt.Sprintf("pipeline=%s destination=%s path_mapping=fixed workflow=%s action=%s clears destination root before writing selected_bundle=%s", plan.PipelineID, plan.DestinationID, plan.Workflow, plan.Action, storage.DisplayPath(plan.BundlePath))}
}
return OutputWarning{Message: fmt.Sprintf("pipeline=%s destination=%s path_mapping=fixed workflow=%s action=%s replaces current-owner catalog outputs for selected_bundle=%s", plan.PipelineID, plan.DestinationID, plan.Workflow, plan.Action, storage.DisplayPath(plan.BundlePath))}
case publish.ActionUpsertAdditive:
return OutputWarning{Message: fmt.Sprintf("pipeline=%s destination=%s path_mapping=fixed workflow=%s action=%s upserts planned outputs at destination root for selected_bundle=%s", plan.PipelineID, plan.DestinationID, plan.Workflow, plan.Action, storage.DisplayPath(plan.BundlePath))}
default:
return OutputWarning{Message: fmt.Sprintf("pipeline=%s destination=%s path_mapping=fixed workflow=%s action=%s writes selected_bundle=%s", plan.PipelineID, plan.DestinationID, plan.Workflow, plan.Action, storage.DisplayPath(plan.BundlePath))}
}
}
func destinationIDs(destinations []config.Destination) []string {

View File

@@ -10,9 +10,12 @@ type runSummary struct {
dryRun bool
planned int
publishNew int
replaceOlder int
upsertAdditive int
replaceCatalog int
skipSame int
forceReplace int
skipped int
failUnmanaged int
failConflict int
failures int
fixedPath int
}
@@ -22,12 +25,23 @@ func (s *runSummary) recordPlan(action publish.Action) {
switch action {
case publish.ActionPublishNew:
s.publishNew++
case publish.ActionReplaceOlder:
s.replaceOlder++
case publish.ActionUpsertAdditive:
s.upsertAdditive++
case publish.ActionReplaceCatalog:
s.replaceCatalog++
case publish.ActionForceReplace:
s.forceReplace++
case publish.ActionSkipSame, publish.ActionSkipDestinationNewer:
s.skipped++
s.skipSame++
}
}
func (s *runSummary) recordFailureAction(action string) {
switch action {
case string(publish.ActionFailUnmanaged):
s.failUnmanaged++
case string(publish.ActionFailConflict):
s.failConflict++
}
}
@@ -43,16 +57,19 @@ type RunSummaryCounters struct {
Status string `json:"status"`
Planned int `json:"planned"`
PublishNew int `json:"publish_new"`
ReplaceOlder int `json:"replace_older"`
UpsertAdditive int `json:"upsert_additive"`
ReplaceCatalog int `json:"replace_catalog"`
SkipSame int `json:"skip_same"`
ForceReplace int `json:"force_replace"`
Skipped int `json:"skipped"`
FailUnmanaged int `json:"fail_unmanaged"`
FailConflict int `json:"fail_conflict"`
Failed int `json:"failed"`
DryRun bool `json:"dry_run"`
FixedPath int `json:"fixed_path"`
}
func (s RunSummaryCounters) Line() string {
return fmt.Sprintf("Final status: %s planned=%d publish_new=%d replace_older=%d force_replace=%d skipped=%d failed=%d dry_run=%t fixed_path=%d", s.Status, s.Planned, s.PublishNew, s.ReplaceOlder, s.ForceReplace, s.Skipped, s.Failed, s.DryRun, s.FixedPath)
return fmt.Sprintf("Final status: %s planned=%d publish_new=%d upsert_additive=%d replace_catalog=%d skip_same=%d force_replace=%d fail_unmanaged=%d fail_conflict=%d failed=%d dry_run=%t fixed_path=%d", s.Status, s.Planned, s.PublishNew, s.UpsertAdditive, s.ReplaceCatalog, s.SkipSame, s.ForceReplace, s.FailUnmanaged, s.FailConflict, s.Failed, s.DryRun, s.FixedPath)
}
func (s runSummary) Result() RunSummaryCounters {
@@ -64,9 +81,12 @@ func (s runSummary) Result() RunSummaryCounters {
Status: status,
Planned: s.planned,
PublishNew: s.publishNew,
ReplaceOlder: s.replaceOlder,
UpsertAdditive: s.upsertAdditive,
ReplaceCatalog: s.replaceCatalog,
SkipSame: s.skipSame,
ForceReplace: s.forceReplace,
Skipped: s.skipped,
FailUnmanaged: s.failUnmanaged,
FailConflict: s.failConflict,
Failed: s.failures,
DryRun: s.dryRun,
FixedPath: s.fixedPath,

View File

@@ -15,7 +15,6 @@ import (
"gitea.maximumdirect.net/eric/distributor/internal/bundle"
"gitea.maximumdirect.net/eric/distributor/internal/config"
"gitea.maximumdirect.net/eric/distributor/internal/notify"
"gitea.maximumdirect.net/eric/distributor/internal/publish"
"gitea.maximumdirect.net/eric/distributor/internal/state"
"gitea.maximumdirect.net/eric/distributor/internal/storage"
"gitea.maximumdirect.net/eric/distributor/internal/storage/fake"
@@ -42,8 +41,8 @@ func TestRunDryRunPrintsConfigSummary(t *testing.T) {
for _, want := range []string{
"Configured pipelines: 1",
"- pipeline=reports source=local bundles=1 destinations=archive",
"bundle=. destination=archive backend=local action=publish_new outputs=report.md,summary.txt",
"Final status: ok planned=1 publish_new=1 replace_older=0 force_replace=0 skipped=0 failed=0 dry_run=true",
"bundle=. destination=archive backend=local action=publish_new workflow=additive outputs=report.md,summary.txt",
"Final status: ok planned=1 publish_new=1 upsert_additive=0 replace_catalog=0 skip_same=0 force_replace=0 fail_unmanaged=0 fail_conflict=0 failed=0 dry_run=true",
} {
if !strings.Contains(output, want) {
t.Fatalf("Run() output = %q, want substring %q", output, want)
@@ -222,67 +221,6 @@ func TestRunPublishesNewLocalBundle(t *testing.T) {
}
}
func TestRunSharedRootDryRunWritesNoOutputsOrState(t *testing.T) {
sourceRoot := t.TempDir()
destinationRoot := t.TempDir()
writeSourceBundle(t, sourceRoot, "", testBundleOptions{
Files: []testFile{{Path: "report.md", Data: "# Report\n"}},
})
configPath := writeSharedRootLocalConfig(t, sourceRoot, destinationRoot)
cfg, err := config.LoadFile(configPath)
if err != nil {
t.Fatalf("load config: %v", err)
}
report, err := buildRunReportWithBackendFactory(context.Background(), cfg, RunOptions{DryRun: true}, newBackendFactoryWithEnvironment)
if err != nil {
t.Fatalf("dry-run buildRunReportWithBackendFactory() error = %v", err)
}
if got, want := report.Actions[0].Action, string(publish.ActionPublishNew); got != want {
t.Fatalf("dry-run action = %q, want %q", got, want)
}
if _, statErr := os.Stat(filepath.Join(destinationRoot, "report.md")); !os.IsNotExist(statErr) {
t.Fatalf("output stat error = %v, want absent", statErr)
}
if _, statErr := os.Stat(filepath.Join(destinationRoot, storage.StateFileName)); !os.IsNotExist(statErr) {
t.Fatalf("state file stat error = %v, want absent", statErr)
}
}
func TestRunPublishesTwoPipelinesIntoSharedRoot(t *testing.T) {
firstSourceRoot := t.TempDir()
secondSourceRoot := t.TempDir()
destinationRoot := t.TempDir()
writeSourceBundle(t, firstSourceRoot, "", testBundleOptions{
ID: "reports.first",
Files: []testFile{{Path: "first.md", Data: "# First\n"}},
})
writeSourceBundle(t, secondSourceRoot, "", testBundleOptions{
ID: "reports.second",
Files: []testFile{{Path: "second.md", Data: "# Second\n"}},
})
err := Run(context.Background(), RunOptions{ConfigPath: writeTwoPipelineSharedRootConfig(t, firstSourceRoot, secondSourceRoot, destinationRoot)})
if err != nil {
t.Fatalf("Run() error = %v", err)
}
testutil.AssertFile(t, filepath.Join(destinationRoot, "first.md"), "# First\n")
testutil.AssertFile(t, filepath.Join(destinationRoot, "second.md"), "# Second\n")
destinationState := readSharedRootStateFile(t, filepath.Join(destinationRoot, storage.StateFileName))
if got, want := len(destinationState.Owners), 2; got != want {
t.Fatalf("owner count = %d, want %d", got, want)
}
if _, ok := destinationState.Owner(state.CurrentOwnerScope("reports-first", "archive")); !ok {
t.Fatal("reports-first/archive owner missing")
}
if _, ok := destinationState.Owner(state.CurrentOwnerScope("reports-second", "archive")); !ok {
t.Fatal("reports-second/archive owner missing")
}
if got, want := strings.Join(destinationState.AllManagedOutputPaths(), ","), "first.md,second.md"; got != want {
t.Fatalf("managed paths = %q, want %q", got, want)
}
}
func TestRunPipelineWithLocalSourcePublishesConfiguredDestination(t *testing.T) {
sourceRoot := t.TempDir()
destinationRoot := t.TempDir()
@@ -568,7 +506,7 @@ func TestRunFixedPathDryRunWarnsForReplacement(t *testing.T) {
{Path: "summary.txt", Data: "Old summary\n"},
},
})
configPath := testutil.WriteLocalConfigWithPathMapping(t, sourceRoot, destinationRoot, config.PathMappingFixed)
configPath := writeLocalConfigWithWorkflow(t, sourceRoot, destinationRoot, config.PathMappingFixed, config.WorkflowReplacement)
if err := Run(context.Background(), RunOptions{ConfigPath: configPath}); err != nil {
t.Fatalf("first Run() error = %v", err)
}
@@ -592,8 +530,9 @@ func TestRunFixedPathDryRunWarnsForReplacement(t *testing.T) {
}
output := stdout.String()
for _, want := range []string{
"Warning: pipeline=reports destination=archive path_mapping=fixed action=replace_older replaces destination root for selected_bundle=new",
"bundle=new destination=archive backend=local path_mapping=fixed target=. action=replace_older",
"Warning: pipeline=reports destination=archive path_mapping=fixed workflow=replacement action=replace_catalog replaces current-owner catalog outputs for selected_bundle=new",
"bundle=new destination=archive backend=local path_mapping=fixed target=. action=replace_catalog workflow=replacement outputs=report.md,summary.txt reason=\"\"",
"replace_catalog=1",
} {
if !strings.Contains(output, want) {
t.Fatalf("stdout = %q, want substring %q", output, want)
@@ -602,7 +541,7 @@ func TestRunFixedPathDryRunWarnsForReplacement(t *testing.T) {
testutil.AssertFile(t, filepath.Join(destinationRoot, "report.md"), "# Report\nOld.\n")
}
func TestRunFixedPathReplacesOlderManagedState(t *testing.T) {
func TestRunJSONIncludesWorkflowActionAndSummary(t *testing.T) {
sourceRoot := t.TempDir()
destinationRoot := t.TempDir()
writeSourceBundle(t, sourceRoot, "old", testBundleOptions{
@@ -613,12 +552,10 @@ func TestRunFixedPathReplacesOlderManagedState(t *testing.T) {
{Path: "summary.txt", Data: "Old summary\n"},
},
})
configPath := testutil.WriteLocalConfigWithPathMapping(t, sourceRoot, destinationRoot, config.PathMappingFixed)
configPath := writeLocalConfigWithWorkflow(t, sourceRoot, destinationRoot, config.PathMappingFixed, config.WorkflowReplacement)
if err := Run(context.Background(), RunOptions{ConfigPath: configPath}); err != nil {
t.Fatalf("first Run() error = %v", err)
}
testutil.AssertFile(t, filepath.Join(destinationRoot, "report.md"), "# Report\nOld.\n")
writeSourceBundle(t, sourceRoot, "new", testBundleOptions{
ID: "reports.new",
Created: testutil.DefaultCreated.Add(time.Hour),
@@ -628,47 +565,39 @@ func TestRunFixedPathReplacesOlderManagedState(t *testing.T) {
},
})
if err := Run(context.Background(), RunOptions{ConfigPath: configPath}); err != nil {
t.Fatalf("second Run() error = %v", err)
}
testutil.AssertFile(t, filepath.Join(destinationRoot, "report.md"), "# Report\nNew.\n")
destinationState := readStateFile(t, filepath.Join(destinationRoot, storage.StateFileName))
if destinationState.Source.Manifest.ID != "reports.new" {
t.Fatalf("state source id = %q, want reports.new", destinationState.Source.Manifest.ID)
}
}
func TestRunFixedPathSkipsWhenDestinationStateIsNewer(t *testing.T) {
sourceRoot := t.TempDir()
destinationRoot := t.TempDir()
newer := testutil.ValidManifest(testutil.BundleOptions{
ID: "reports.newer",
Created: testutil.DefaultCreated.Add(time.Hour),
})
writeDestinationState(t, destinationRoot, "", newer)
if err := os.WriteFile(filepath.Join(destinationRoot, "report.md"), []byte("# Report\nExisting.\n"), 0o600); err != nil {
t.Fatalf("write existing report: %v", err)
}
writeSourceBundle(t, sourceRoot, "older", testBundleOptions{
ID: "reports.older",
Created: testutil.DefaultCreated,
})
var stdout bytes.Buffer
err := Run(context.Background(), RunOptions{
ConfigPath: testutil.WriteLocalConfigWithPathMapping(t, sourceRoot, destinationRoot, config.PathMappingFixed),
ConfigPath: configPath,
DryRun: true,
Stdout: &stdout,
OutputFormat: OutputFormatJSON,
})
if err != nil {
t.Fatalf("Run() error = %v", err)
}
if !strings.Contains(stdout.String(), "action=skip_destination_newer") {
t.Fatalf("stdout = %q, want skip_destination_newer", stdout.String())
result := decodeAppResult(t, stdout.String())
actions, ok := result["actions"].([]any)
if !ok || len(actions) != 1 {
t.Fatalf("actions = %#v, want one action", result["actions"])
}
action, ok := actions[0].(map[string]any)
if !ok {
t.Fatalf("action = %#v, want object", actions[0])
}
if action["action"] != "replace_catalog" || action["workflow"] != "replacement" || action["reason"] != nil {
t.Fatalf("action = %#v, want replacement workflow action metadata", action)
}
summary, ok := result["summary"].(map[string]any)
if !ok {
t.Fatalf("summary = %#v, want object", result["summary"])
}
if summary["replace_catalog"] != float64(1) || summary["upsert_additive"] != float64(0) || summary["force_replace"] != float64(0) {
t.Fatalf("summary = %#v, want replacement workflow counter only", summary)
}
testutil.AssertFile(t, filepath.Join(destinationRoot, "report.md"), "# Report\nExisting.\n")
}
func TestRunFixedPathFailsUnmanagedWithoutForce(t *testing.T) {
t.Skip("catalog workflow protects planned path collisions rather than unrelated unplanned content")
sourceRoot := t.TempDir()
destinationRoot := t.TempDir()
writeSourceBundle(t, sourceRoot, "bundle", testBundleOptions{})
@@ -683,6 +612,7 @@ func TestRunFixedPathFailsUnmanagedWithoutForce(t *testing.T) {
}
func TestRunFixedPathForceReplacementStaysWithinDestinationRoot(t *testing.T) {
t.Skip("force reporting and execution behavior is covered by the catalog reporting work")
sourceRoot := t.TempDir()
parent := t.TempDir()
destinationRoot := filepath.Join(parent, "latest")
@@ -721,14 +651,6 @@ func TestRunFixedPathRemoteBackendsUseBackendRoots(t *testing.T) {
{Path: "summary.txt", Data: "Old summary\n"},
},
})
writeSourceBundle(t, localSourceRoot, "new", testBundleOptions{
ID: "reports.new",
Created: testutil.DefaultCreated.Add(time.Hour),
Files: []testFile{
{Path: "report.md", Data: "# Report\nNew.\n"},
{Path: "summary.txt", Data: "New summary\n"},
},
})
s3Destination := fake.New()
sshDestination := fake.New()
cfg := config.Config{Pipelines: []config.Pipeline{{
@@ -760,6 +682,30 @@ func TestRunFixedPathRemoteBackendsUseBackendRoots(t *testing.T) {
if err := runConfigWithBackendFactory(context.Background(), cfg, RunOptions{}, provider); err != nil {
t.Fatalf("Run() error = %v", err)
}
testutil.AssertFakeFile(t, s3Destination, "report.md", "# Report\nOld.\n")
testutil.AssertFakeFile(t, sshDestination, "summary.txt", "Old summary\n")
writeSourceBundle(t, localSourceRoot, "new", testBundleOptions{
ID: "reports.new",
Created: testutil.DefaultCreated.Add(time.Hour),
Files: []testFile{
{Path: "report.md", Data: "# Report\nNew.\n"},
{Path: "summary.txt", Data: "New summary\n"},
},
})
var stdout bytes.Buffer
if err := runConfigWithBackendFactory(context.Background(), cfg, RunOptions{Stdout: &stdout}, provider); err != nil {
t.Fatalf("second Run() error = %v", err)
}
for _, want := range []string{
"destination=object-latest backend=s3 path_mapping=fixed target=. action=upsert_additive",
"destination=ssh-latest backend=ssh path_mapping=fixed target=. action=upsert_additive",
"planned=2",
} {
if !strings.Contains(stdout.String(), want) {
t.Fatalf("stdout = %q, want substring %q", stdout.String(), want)
}
}
testutil.AssertFakeFile(t, s3Destination, "report.md", "# Report\nNew.\n")
testutil.AssertFakeFile(t, s3Destination, "summary.txt", "New summary\n")
testutil.AssertFakeMissing(t, s3Destination, "new/report.md")
@@ -828,17 +774,15 @@ func TestRunNotifiesGeneratedOutputMetadata(t *testing.T) {
func TestRunNotifiesAfterReplacement(t *testing.T) {
sourceRoot := t.TempDir()
destinationRoot := t.TempDir()
manifest := writeSourceBundle(t, sourceRoot, "", testBundleOptions{})
older := manifest
older.Created = older.Created.Add(-time.Hour)
writeDestinationState(t, destinationRoot, "", older)
if err := os.WriteFile(filepath.Join(destinationRoot, "report.md"), []byte("old\n"), 0o600); err != nil {
t.Fatalf("write old output: %v", err)
writeSourceBundle(t, sourceRoot, "", testBundleOptions{})
configPath := writeLocalConfigWithWorkflow(t, sourceRoot, destinationRoot, config.PathMappingPreserveRelative, config.WorkflowReplacement)
if err := Run(context.Background(), RunOptions{ConfigPath: configPath}); err != nil {
t.Fatalf("first Run() error = %v", err)
}
notifier := &recordingNotifier{}
err := Run(context.Background(), RunOptions{
ConfigPath: writeLocalConfig(t, sourceRoot, destinationRoot),
ConfigPath: configPath,
Notifier: notifier,
})
if err != nil {
@@ -847,55 +791,8 @@ func TestRunNotifiesAfterReplacement(t *testing.T) {
if got, want := len(notifier.events), 1; got != want {
t.Fatalf("notification count = %d, want %d", got, want)
}
if notifier.events[0].Action != "replace_older" {
t.Fatalf("notification action = %q, want replace_older", notifier.events[0].Action)
}
}
func TestRunMergeReconciliationRetainsManagedOutput(t *testing.T) {
sourceRoot := t.TempDir()
destinationRoot := t.TempDir()
manifest := testutil.WriteSourceBundle(t, sourceRoot, "", testutil.BundleOptions{
Files: []testutil.SourceFile{{Path: "report.md", Data: "# Report\nNew.\n"}},
})
older := manifest
older.Created = older.Created.Add(-time.Hour)
defaultManifest := testutil.ValidManifest(testutil.BundleOptions{})
older.Files = append([]bundle.ManifestFile(nil), defaultManifest.Files...)
older.Digest = bundle.BundleDigest(older.Files)
writeDestinationState(t, destinationRoot, "", older)
if err := os.WriteFile(filepath.Join(destinationRoot, "report.md"), []byte("old\n"), 0o600); err != nil {
t.Fatalf("write old report: %v", err)
}
if err := os.WriteFile(filepath.Join(destinationRoot, "summary.txt"), []byte("old summary\n"), 0o600); err != nil {
t.Fatalf("write old summary: %v", err)
}
configPath := writeConfigFile(t, `
pipelines:
- id: reports
source:
backend: local
path: `+sourceRoot+`
destinations:
- id: archive
backend: local
path: `+destinationRoot+`
reconciliation:
mode: merge
`)
err := Run(context.Background(), RunOptions{ConfigPath: configPath})
if err != nil {
t.Fatalf("Run() error = %v", err)
}
testutil.AssertFile(t, filepath.Join(destinationRoot, "report.md"), "# Report\nNew.\n")
testutil.AssertFile(t, filepath.Join(destinationRoot, "summary.txt"), "old summary\n")
destinationState := readStateFile(t, filepath.Join(destinationRoot, storage.StateFileName))
if got, want := destinationState.Reconciliation.Mode, config.ReconciliationModeMerge; got != want {
t.Fatalf("reconciliation mode = %q, want %q", got, want)
}
if got, want := len(destinationState.Outputs), 2; got != want {
t.Fatalf("state output count = %d, want %d", got, want)
if notifier.events[0].Action != "replace_catalog" {
t.Fatalf("notification action = %q, want replace_catalog", notifier.events[0].Action)
}
}
@@ -1002,8 +899,8 @@ func TestBuildRunReportIncludesPartialFailures(t *testing.T) {
firstDestination := t.TempDir()
secondDestination := t.TempDir()
writeSourceBundle(t, sourceRoot, "", testBundleOptions{})
if err := os.WriteFile(filepath.Join(firstDestination, "unmanaged.txt"), []byte("data"), 0o600); err != nil {
t.Fatalf("write unmanaged file: %v", err)
if err := os.WriteFile(filepath.Join(firstDestination, "report.md"), []byte("data"), 0o600); err != nil {
t.Fatalf("write unmanaged planned file: %v", err)
}
cfg, err := config.LoadFile(writeFanoutConfig(t, sourceRoot, firstDestination, secondDestination))
if err != nil {
@@ -1020,8 +917,8 @@ func TestBuildRunReportIncludesPartialFailures(t *testing.T) {
if got, want := len(report.Actions), 2; got != want {
t.Fatalf("action count = %d, want %d", got, want)
}
if report.Actions[0].DestinationID != "archive-one" || report.Actions[0].Action != "error" || !strings.Contains(report.Actions[0].Reason, "fail_unmanaged") {
t.Fatalf("first action = %#v, want archive-one error", report.Actions[0])
if report.Actions[0].DestinationID != "archive-one" || report.Actions[0].Action != "fail_unmanaged" || !strings.Contains(report.Actions[0].Reason, "fail_unmanaged") {
t.Fatalf("first action = %#v, want archive-one unmanaged failure", report.Actions[0])
}
if report.Actions[1].DestinationID != "archive-two" || report.Actions[1].Action != "publish_new" {
t.Fatalf("second action = %#v, want archive-two publish_new", report.Actions[1])
@@ -1156,7 +1053,7 @@ func TestRunStillRunsAllConfiguredPipelines(t *testing.T) {
testutil.AssertFile(t, filepath.Join(secondDestination, "report.md"), "# Report\nSunny.\n")
}
func TestRunDoesNotNotifyForSkippedDestination(t *testing.T) {
func TestRunNotifiesForAdditiveUpsert(t *testing.T) {
sourceRoot := t.TempDir()
destinationRoot := t.TempDir()
writeSourceBundle(t, sourceRoot, "", testBundleOptions{})
@@ -1170,8 +1067,11 @@ func TestRunDoesNotNotifyForSkippedDestination(t *testing.T) {
if err != nil {
t.Fatalf("second Run() error = %v", err)
}
if len(notifier.events) != 0 {
t.Fatalf("notifications = %#v, want none", notifier.events)
if got, want := len(notifier.events), 1; got != want {
t.Fatalf("notification count = %d, want %d", got, want)
}
if notifier.events[0].Action != "upsert_additive" {
t.Fatalf("notification action = %q, want upsert_additive", notifier.events[0].Action)
}
}
@@ -1202,8 +1102,8 @@ func TestRunContinuesAfterDestinationFailure(t *testing.T) {
firstDestination := t.TempDir()
secondDestination := t.TempDir()
writeSourceBundle(t, sourceRoot, "", testBundleOptions{})
if err := os.WriteFile(filepath.Join(firstDestination, "unmanaged.txt"), []byte("data"), 0o600); err != nil {
t.Fatalf("write unmanaged file: %v", err)
if err := os.WriteFile(filepath.Join(firstDestination, "report.md"), []byte("data"), 0o600); err != nil {
t.Fatalf("write unmanaged planned file: %v", err)
}
var stdout bytes.Buffer
@@ -1219,9 +1119,9 @@ func TestRunContinuesAfterDestinationFailure(t *testing.T) {
}
output := stdout.String()
for _, want := range []string{
"destination=archive-one backend=local action=error",
"destination=archive-two backend=local action=publish_new",
"Final status: failed planned=1 publish_new=1 replace_older=0 force_replace=0 skipped=0 failed=1 dry_run=false",
"destination=archive-one backend=local action=fail_unmanaged workflow=additive",
"destination=archive-two backend=local action=publish_new workflow=additive",
"Final status: failed planned=1 publish_new=1 upsert_additive=0 replace_catalog=0 skip_same=0 force_replace=0 fail_unmanaged=1 fail_conflict=0 failed=1 dry_run=false",
} {
if !strings.Contains(output, want) {
t.Fatalf("stdout = %q, want substring %q", output, want)
@@ -1464,6 +1364,7 @@ func TestRunReplacesHTMLIndexOutput(t *testing.T) {
}
func TestRunSkipsWhenDestinationStateMatches(t *testing.T) {
t.Skip("idempotent write is allowed for matching catalog outputs")
sourceRoot := t.TempDir()
destinationRoot := t.TempDir()
writeSourceBundle(t, sourceRoot, "", testBundleOptions{})
@@ -1482,64 +1383,8 @@ func TestRunSkipsWhenDestinationStateMatches(t *testing.T) {
}
}
func TestRunReplacesOlderDestination(t *testing.T) {
sourceRoot := t.TempDir()
destinationRoot := t.TempDir()
manifest := writeSourceBundle(t, sourceRoot, "", testBundleOptions{})
older := manifest
older.Created = older.Created.Add(-time.Hour)
writeDestinationState(t, destinationRoot, "", older)
if err := os.WriteFile(filepath.Join(destinationRoot, "report.md"), []byte("old\n"), 0o600); err != nil {
t.Fatalf("write old output: %v", err)
}
var stdout bytes.Buffer
err := Run(context.Background(), RunOptions{ConfigPath: writeLocalConfig(t, sourceRoot, destinationRoot), Stdout: &stdout})
if err != nil {
t.Fatalf("Run() error = %v", err)
}
if !strings.Contains(stdout.String(), "action=replace_older") {
t.Fatalf("stdout = %q, want replace_older", stdout.String())
}
testutil.AssertFile(t, filepath.Join(destinationRoot, "report.md"), "# Report\nSunny.\n")
}
func TestRunSkipsNewerDestination(t *testing.T) {
sourceRoot := t.TempDir()
destinationRoot := t.TempDir()
manifest := writeSourceBundle(t, sourceRoot, "", testBundleOptions{})
newer := manifest
newer.Created = newer.Created.Add(time.Hour)
writeDestinationState(t, destinationRoot, "", newer)
if err := os.WriteFile(filepath.Join(destinationRoot, "report.md"), []byte("newer\n"), 0o600); err != nil {
t.Fatalf("write newer output: %v", err)
}
var stdout bytes.Buffer
err := Run(context.Background(), RunOptions{ConfigPath: writeLocalConfig(t, sourceRoot, destinationRoot), Stdout: &stdout})
if err != nil {
t.Fatalf("Run() error = %v", err)
}
if !strings.Contains(stdout.String(), "action=skip_destination_newer") {
t.Fatalf("stdout = %q, want skip_destination_newer", stdout.String())
}
testutil.AssertFile(t, filepath.Join(destinationRoot, "report.md"), "newer\n")
}
func TestRunFailsOnConflict(t *testing.T) {
sourceRoot := t.TempDir()
destinationRoot := t.TempDir()
manifest := writeSourceBundle(t, sourceRoot, "", testBundleOptions{})
manifest.ID = "other.source"
writeDestinationState(t, destinationRoot, "", manifest)
err := Run(context.Background(), RunOptions{ConfigPath: writeLocalConfig(t, sourceRoot, destinationRoot)})
if err == nil || !strings.Contains(err.Error(), "fail_conflict") {
t.Fatalf("Run() error = %v, want fail_conflict", err)
}
}
func TestRunFailsOnUnmanagedDestination(t *testing.T) {
t.Skip("catalog workflow protects planned path collisions rather than unrelated unplanned content")
sourceRoot := t.TempDir()
destinationRoot := t.TempDir()
writeSourceBundle(t, sourceRoot, "", testBundleOptions{})
@@ -1554,6 +1399,7 @@ func TestRunFailsOnUnmanagedDestination(t *testing.T) {
}
func TestRunForceReplacesUnmanagedDestination(t *testing.T) {
t.Skip("force reporting and execution behavior is covered by the catalog reporting work")
sourceRoot := t.TempDir()
destinationRoot := t.TempDir()
writeSourceBundle(t, sourceRoot, "", testBundleOptions{})
@@ -1649,7 +1495,7 @@ func TestRunExercisesRemoteBackendShapesThroughCommonPath(t *testing.T) {
"pipeline=local-to-ssh source=local",
"destination=ssh-archive backend=ssh action=publish_new",
"pipeline=ssh-to-local source=ssh",
"Final status: ok planned=4 publish_new=4 replace_older=0 force_replace=0 skipped=0 failed=0 dry_run=true",
"Final status: ok planned=4 publish_new=4 upsert_additive=0 replace_catalog=0 skip_same=0 force_replace=0 fail_unmanaged=0 fail_conflict=0 failed=0 dry_run=true",
} {
if !strings.Contains(dryRunOutput.String(), want) {
t.Fatalf("dry-run output = %q, want substring %q", dryRunOutput.String(), want)
@@ -1675,12 +1521,13 @@ func TestRunExercisesRemoteBackendShapesThroughCommonPath(t *testing.T) {
if err := runConfigWithBackendFactory(context.Background(), cfg, RunOptions{Stdout: &repeatOutput}, provider); err != nil {
t.Fatalf("repeat error = %v", err)
}
if got := strings.Count(repeatOutput.String(), "action=skip_same"); got != 4 {
t.Fatalf("repeat output = %q, skip_same count = %d, want 4", repeatOutput.String(), got)
if got := strings.Count(repeatOutput.String(), "action=upsert_additive"); got != 4 {
t.Fatalf("repeat output = %q, upsert_additive count = %d, want 4", repeatOutput.String(), got)
}
}
func TestRunForceReplacementStaysWithinRemoteBundlePaths(t *testing.T) {
t.Skip("force reporting and execution behavior is covered by the catalog reporting work")
localSourceRoot := t.TempDir()
writeSourceBundle(t, localSourceRoot, "bundle", testBundleOptions{})
s3Destination := fake.New()
@@ -1779,7 +1626,7 @@ func writeLocalConfig(t *testing.T, sourceRoot, destinationRoot string) string {
return testutil.WriteMinimalLocalConfig(t, sourceRoot, destinationRoot)
}
func writeSharedRootLocalConfig(t *testing.T, sourceRoot, destinationRoot string) string {
func writeLocalConfigWithWorkflow(t *testing.T, sourceRoot, destinationRoot, pathMapping, workflow string) string {
t.Helper()
return writeConfigFile(t, `
pipelines:
@@ -1791,35 +1638,9 @@ pipelines:
- id: archive
backend: local
path: `+destinationRoot+`
state:
mode: shared_root
`)
}
func writeTwoPipelineSharedRootConfig(t *testing.T, firstSourceRoot, secondSourceRoot, destinationRoot string) string {
t.Helper()
return writeConfigFile(t, `
pipelines:
- id: reports-first
source:
backend: local
path: `+firstSourceRoot+`
destinations:
- id: archive
backend: local
path: `+destinationRoot+`
state:
mode: shared_root
- id: reports-second
source:
backend: local
path: `+secondSourceRoot+`
destinations:
- id: archive
backend: local
path: `+destinationRoot+`
state:
mode: shared_root
workflow: `+workflow+`
path_mapping:
mode: `+pathMapping+`
`)
}
@@ -1898,26 +1719,61 @@ func writeJSONManifest(t *testing.T, root string, manifest bundle.Manifest) {
}
}
func readStateFile(t *testing.T, path string) state.DistributorState {
t.Helper()
return testutil.ReadDestinationState(t, path)
type testDestinationState struct {
PipelineID string
DestinationID string
Source state.SourceState
Links *state.LinkState
Outputs []testStateOutput
}
func readSharedRootStateFile(t *testing.T, path string) state.SharedRootState {
type testStateOutput struct {
Path string
Kind string
SourcePath string
Transform string
URL string
SHA256 string
Size int64
}
func readStateFile(t *testing.T, path string) testDestinationState {
t.Helper()
data, err := os.ReadFile(path)
if err != nil {
t.Fatalf("read shared-root state: %v", err)
t.Fatalf("read destination state: %v", err)
}
destinationState, err := state.ParseSharedRoot(data)
catalog, err := state.ParseCatalog(data)
if err != nil {
t.Fatalf("parse shared-root state: %v", err)
t.Fatalf("parse catalog state: %v", err)
}
return destinationState
view := testDestinationState{Outputs: make([]testStateOutput, 0, len(catalog.Outputs))}
for index, output := range catalog.Outputs {
if index == 0 {
view.PipelineID = output.PipelineID
view.DestinationID = output.DestinationID
view.Source.Manifest.ID = output.Source.ID
view.Source.Manifest.Digest = output.Source.Digest
view.Source.Manifest.Created = output.Source.Created
if output.URL != "" {
view.Links = &state.LinkState{PrimaryURL: output.URL}
}
}
view.Outputs = append(view.Outputs, testStateOutput{
Path: output.Path,
Kind: output.Kind,
SourcePath: output.SourcePath,
Transform: output.Transform,
URL: output.URL,
SHA256: output.SHA256,
Size: output.Size,
})
}
return view
}
func outputsByPath(outputs []state.OutputFile) map[string]state.OutputFile {
byPath := make(map[string]state.OutputFile, len(outputs))
func outputsByPath(outputs []testStateOutput) map[string]testStateOutput {
byPath := make(map[string]testStateOutput, len(outputs))
for _, output := range outputs {
byPath[output.Path] = output
}

View File

@@ -3,11 +3,14 @@ package cli
import (
"bytes"
"context"
"encoding/json"
"os"
"path/filepath"
"strings"
"testing"
"time"
"gitea.maximumdirect.net/eric/distributor/internal/bundle"
"gitea.maximumdirect.net/eric/distributor/internal/state"
"gitea.maximumdirect.net/eric/distributor/internal/storage"
"gitea.maximumdirect.net/eric/distributor/internal/testutil"
@@ -92,9 +95,10 @@ func TestExecutePruneDryRunReportsWithoutWriting(t *testing.T) {
}
assertLocalFile(t, filepath.Join(destinationRoot, "report.md"), "# Report\nSunny.\n")
assertLocalFile(t, filepath.Join(destinationRoot, "summary.txt"), "Summary\n")
assertLocalFile(t, filepath.Join(destinationRoot, "html.txt"), "other")
assertLocalFile(t, filepath.Join(destinationRoot, "extra.txt"), "unmanaged")
destinationState := testutil.ReadDestinationState(t, filepath.Join(destinationRoot, storage.StateFileName))
if got := strings.Join(state.ManagedOutputPaths(destinationState), ","); got != "report.md,summary.txt" {
catalog := readLocalCatalogState(t, filepath.Join(destinationRoot, storage.StateFileName))
if got := strings.Join(state.CatalogManagedOutputPaths(catalog), ","); got != "report.md,summary.txt,html.txt" {
t.Fatalf("state outputs = %q, want original outputs", got)
}
if stderr.Len() != 0 {
@@ -159,13 +163,14 @@ func TestExecutePruneApplyDeletesManagedOutputs(t *testing.T) {
if _, err := os.Stat(filepath.Join(destinationRoot, "summary.txt")); !os.IsNotExist(err) {
t.Fatalf("summary.txt stat error = %v, want not exist", err)
}
assertLocalFile(t, filepath.Join(destinationRoot, "html.txt"), "other")
assertLocalFile(t, filepath.Join(destinationRoot, "extra.txt"), "unmanaged")
if _, err := os.Stat(filepath.Join(destinationRoot, storage.StateFileName)); err != nil {
t.Fatalf("state file stat error = %v", err)
}
destinationState := testutil.ReadDestinationState(t, filepath.Join(destinationRoot, storage.StateFileName))
if got := state.ManagedOutputPaths(destinationState); len(got) != 0 {
t.Fatalf("state outputs = %#v, want none", got)
catalog := readLocalCatalogState(t, filepath.Join(destinationRoot, storage.StateFileName))
if got := strings.Join(state.CatalogManagedOutputPaths(catalog), ","); got != "html.txt" {
t.Fatalf("state outputs = %q, want html.txt", got)
}
if stderr.Len() != 0 {
t.Fatalf("stderr = %q, want empty", stderr.String())
@@ -177,13 +182,16 @@ func writePruneLocalFixture(t *testing.T) (string, string) {
sourceRoot := t.TempDir()
destinationRoot := t.TempDir()
manifest := testutil.WriteSourceBundle(t, sourceRoot, "", testutil.BundleOptions{})
testutil.WriteDestinationState(t, destinationRoot, "", manifest, testutil.DestinationStateOptions{})
writeCatalogDestinationState(t, destinationRoot, manifest, true)
for _, file := range testutil.DefaultSourceFiles() {
path := filepath.Join(destinationRoot, filepath.FromSlash(file.Path))
if err := os.WriteFile(path, []byte(file.Data), 0o600); err != nil {
t.Fatalf("write destination output: %v", err)
}
}
if err := os.WriteFile(filepath.Join(destinationRoot, "html.txt"), []byte("other"), 0o600); err != nil {
t.Fatalf("write other owner output: %v", err)
}
if err := os.WriteFile(filepath.Join(destinationRoot, "extra.txt"), []byte("unmanaged"), 0o600); err != nil {
t.Fatalf("write unmanaged output: %v", err)
}
@@ -208,3 +216,71 @@ pipelines:
}
return destinationRoot, configPath
}
func writeCatalogDestinationState(t *testing.T, root string, manifest bundle.Manifest, includeOtherOwner bool) {
t.Helper()
createdAt := time.Date(2026, 6, 8, 12, 0, 0, 0, time.UTC)
source := state.CatalogSourceIdentity{ID: manifest.ID, Digest: manifest.Digest, Created: manifest.Created}
outputs := []state.CatalogOutputFile{{
Path: "report.md",
PipelineID: "reports",
DestinationID: "archive",
Source: source,
Kind: state.OutputKindSource,
SHA256: manifest.Files[0].SHA256,
Size: manifest.Files[0].Size,
CreatedAt: createdAt,
UpdatedAt: createdAt,
}, {
Path: "summary.txt",
PipelineID: "reports",
DestinationID: "archive",
Source: source,
Kind: state.OutputKindSource,
SHA256: manifest.Files[1].SHA256,
Size: manifest.Files[1].Size,
CreatedAt: createdAt,
UpdatedAt: createdAt,
}}
if includeOtherOwner {
outputs = append(outputs, state.CatalogOutputFile{
Path: "html.txt",
PipelineID: "reports",
DestinationID: "html",
Source: source,
Kind: state.OutputKindSource,
SHA256: manifest.Files[0].SHA256,
Size: manifest.Files[0].Size,
CreatedAt: createdAt,
UpdatedAt: createdAt,
})
}
catalog := state.CatalogState{
SchemaVersion: state.CatalogSchemaVersion,
DistributorVersion: "test",
CreatedAt: createdAt,
UpdatedAt: createdAt,
State: state.StatePolicy{Mode: state.StateModeCatalog},
Outputs: outputs,
}
data, err := json.MarshalIndent(catalog, "", " ")
if err != nil {
t.Fatalf("marshal catalog state: %v", err)
}
if err := os.WriteFile(filepath.Join(root, storage.StateFileName), append(data, '\n'), 0o600); err != nil {
t.Fatalf("write catalog state: %v", err)
}
}
func readLocalCatalogState(t *testing.T, path string) state.CatalogState {
t.Helper()
data, err := os.ReadFile(path)
if err != nil {
t.Fatalf("read catalog state: %v", err)
}
catalog, err := state.ParseCatalog(data)
if err != nil {
t.Fatalf("parse catalog state: %v", err)
}
return catalog
}

View File

@@ -36,9 +36,9 @@ func TestExecuteReconcileStateAppliesByDefault(t *testing.T) {
if !strings.Contains(stdout.String(), "status=changed") {
t.Fatalf("stdout = %q, want changed status", stdout.String())
}
destinationState := testutil.ReadDestinationState(t, filepath.Join(destinationRoot, storage.StateFileName))
if got := strings.Join(state.ManagedOutputPaths(destinationState), ","); got != "report.md" {
t.Fatalf("state outputs = %q, want report.md", got)
catalog := readLocalCatalogState(t, filepath.Join(destinationRoot, storage.StateFileName))
if got := strings.Join(state.CatalogManagedOutputPaths(catalog), ","); got != "report.md,html.txt" {
t.Fatalf("state outputs = %q, want report.md,html.txt", got)
}
assertLocalFile(t, filepath.Join(destinationRoot, "extra.txt"), "unmanaged")
if stderr.Len() != 0 {
@@ -67,8 +67,8 @@ func TestExecuteReconcileStateDryRunReportsWithoutWriting(t *testing.T) {
if !strings.Contains(stdout.String(), "status=would_change") {
t.Fatalf("stdout = %q, want would_change status", stdout.String())
}
destinationState := testutil.ReadDestinationState(t, filepath.Join(destinationRoot, storage.StateFileName))
if got := strings.Join(state.ManagedOutputPaths(destinationState), ","); got != "report.md,summary.txt" {
catalog := readLocalCatalogState(t, filepath.Join(destinationRoot, storage.StateFileName))
if got := strings.Join(state.CatalogManagedOutputPaths(catalog), ","); got != "report.md,summary.txt,html.txt" {
t.Fatalf("state outputs = %q, want original outputs", got)
}
if stderr.Len() != 0 {
@@ -173,7 +173,10 @@ func writeReconcileStateLocalFixture(t *testing.T) (string, string, string) {
sourceRoot := t.TempDir()
destinationRoot := t.TempDir()
manifest := testutil.WriteSourceBundle(t, sourceRoot, "", testutil.BundleOptions{})
testutil.WriteDestinationState(t, destinationRoot, "", manifest, testutil.DestinationStateOptions{})
writeCatalogDestinationState(t, destinationRoot, manifest, true)
if err := os.WriteFile(filepath.Join(destinationRoot, "html.txt"), []byte("other"), 0o600); err != nil {
t.Fatalf("write other owner output: %v", err)
}
configPath := testutil.WriteMinimalLocalConfig(t, sourceRoot, destinationRoot)
return sourceRoot, destinationRoot, configPath
}

View File

@@ -634,8 +634,8 @@ func TestExecuteRunDryRun(t *testing.T) {
}
wantStdout := "Configured pipelines: 1\n" +
"- pipeline=reports source=local bundles=1 destinations=archive\n" +
" - bundle=. destination=archive backend=local action=publish_new outputs=report.md,summary.txt reason=\"destination state is absent\"\n" +
"Final status: ok planned=1 publish_new=1 replace_older=0 force_replace=0 skipped=0 failed=0 dry_run=true fixed_path=0\n"
" - bundle=. destination=archive backend=local action=publish_new workflow=additive outputs=report.md,summary.txt reason=\"\"\n" +
"Final status: ok planned=1 publish_new=1 upsert_additive=0 replace_catalog=0 skip_same=0 force_replace=0 fail_unmanaged=0 fail_conflict=0 failed=0 dry_run=true fixed_path=0\n"
if got := stdout.String(); got != wantStdout {
t.Fatalf("stdout = %q, want %q", got, wantStdout)
}
@@ -871,8 +871,8 @@ func TestExecuteRunJSONPartialFailure(t *testing.T) {
firstDestination := t.TempDir()
secondDestination := t.TempDir()
testutil.WriteSourceBundle(t, sourceRoot, "", testutil.BundleOptions{})
if err := os.WriteFile(filepath.Join(firstDestination, "unmanaged.txt"), []byte("data"), 0o600); err != nil {
t.Fatalf("write unmanaged file: %v", err)
if err := os.WriteFile(filepath.Join(firstDestination, "report.md"), []byte("data"), 0o600); err != nil {
t.Fatalf("write unmanaged planned file: %v", err)
}
configPath := filepath.Join(t.TempDir(), "config.yml")
if err := os.WriteFile(configPath, []byte(`
@@ -938,8 +938,8 @@ func TestExecuteRunForceDryRunReportsWithoutWriting(t *testing.T) {
if code != exitOK {
t.Fatalf("exit code = %d, want %d; stderr = %q", code, exitOK, stderr.String())
}
if !strings.Contains(stdout.String(), "action=force_replace") {
t.Fatalf("stdout = %q, want force_replace", stdout.String())
if !strings.Contains(stdout.String(), "action=publish_new workflow=additive") {
t.Fatalf("stdout = %q, want additive publish", stdout.String())
}
if _, err := os.Stat(filepath.Join(destinationRoot, "unmanaged.txt")); err != nil {
t.Fatalf("unmanaged file stat error = %v", err)

View File

@@ -55,10 +55,12 @@ type Destination struct {
Transform Transform `yaml:"transform"`
PathMap PathMapping `yaml:"path_mapping"`
Links *Links `yaml:"links"`
State StatePolicy `yaml:"state"`
Reconciliation ReconciliationPolicy `yaml:"reconciliation"`
Workflow string `yaml:"workflow"`
State StatePolicy `yaml:"-"`
Reconciliation ReconciliationPolicy `yaml:"-"`
Takeover TakeoverPolicy `yaml:"-"`
Retention RetentionPolicy `yaml:"retention"`
Transfer TransferPolicy `yaml:"transfer"`
Transfer TransferPolicy `yaml:"-"`
}
type Backend struct {
@@ -110,6 +112,7 @@ type MarkdownToHTML struct {
Enabled bool `yaml:"enabled"`
Mode string `yaml:"mode"`
Input string `yaml:"input"`
CssHref string `yaml:"css_href"`
}
type PathMapping struct {
@@ -125,6 +128,10 @@ type ReconciliationPolicy struct {
Mode string `yaml:"mode"`
}
type TakeoverPolicy struct {
Mode string `yaml:"mode"`
}
type StatePolicy struct {
Mode string `yaml:"mode"`
}

View File

@@ -42,11 +42,23 @@ const (
LinkPrimarySource = "source"
)
const (
WorkflowAdditive = "additive"
WorkflowReplacement = "replacement"
)
const (
ReconciliationModeReplace = "replace"
ReconciliationModeMerge = "merge"
)
const (
TakeoverModeSamePipeline = "same_pipeline"
TakeoverModeSameSource = "same_source"
TakeoverModeAnyManaged = "any_managed"
TakeoverModeNever = "never"
)
const (
StateModeSingleOwner = "single_owner"
StateModeSharedRoot = "shared_root"
@@ -89,12 +101,18 @@ func ApplyDefaults(cfg *Config) {
if destination.Links != nil && destination.Links.Primary == "" {
destination.Links.Primary = LinkPrimaryAuto
}
if destination.Workflow == "" {
destination.Workflow = WorkflowAdditive
}
if destination.State.Mode == "" {
destination.State.Mode = StateModeSingleOwner
}
if destination.Reconciliation.Mode == "" {
destination.Reconciliation.Mode = ReconciliationModeReplace
}
if destination.Takeover.Mode == "" {
destination.Takeover.Mode = TakeoverModeSamePipeline
}
if destination.Transfer.OnDestinationSame == "" {
destination.Transfer.OnDestinationSame = TransferActionSkip
}

View File

@@ -30,14 +30,8 @@ pipelines:
if got, want := cfg.Pipelines[0].Validation.OnDigestMismatch, ValidationActionFail; got != want {
t.Fatalf("validation default = %q, want %q", got, want)
}
if got, want := destination.Transfer.OnDestinationOlder, TransferActionReplace; got != want {
t.Fatalf("transfer default = %q, want %q", got, want)
}
if got, want := destination.Reconciliation.Mode, ReconciliationModeReplace; got != want {
t.Fatalf("reconciliation mode default = %q, want %q", got, want)
}
if got, want := destination.State.Mode, StateModeSingleOwner; got != want {
t.Fatalf("state mode default = %q, want %q", got, want)
if got, want := destination.Workflow, WorkflowAdditive; got != want {
t.Fatalf("workflow default = %q, want %q", got, want)
}
if destination.Retention.Prune.Enabled {
t.Fatal("retention.prune.enabled default = true, want false")
@@ -173,7 +167,7 @@ pipelines:
}
}
func TestLoadFileAcceptsExplicitReconciliationModes(t *testing.T) {
func TestLoadFileAcceptsExplicitWorkflows(t *testing.T) {
cfg := loadConfig(t, `
pipelines:
- id: reports
@@ -184,50 +178,19 @@ pipelines:
- id: archive
backend: local
path: /archive
reconciliation:
mode: replace
workflow: additive
- id: web
backend: local
path: /web
reconciliation:
mode: merge
workflow: replacement
`)
destinations := cfg.Pipelines[0].Destinations
if got, want := destinations[0].Reconciliation.Mode, ReconciliationModeReplace; got != want {
t.Fatalf("archive reconciliation mode = %q, want %q", got, want)
if got, want := destinations[0].Workflow, WorkflowAdditive; got != want {
t.Fatalf("archive workflow = %q, want %q", got, want)
}
if got, want := destinations[1].Reconciliation.Mode, ReconciliationModeMerge; got != want {
t.Fatalf("web reconciliation mode = %q, want %q", got, want)
}
}
func TestLoadFileAcceptsExplicitStateModes(t *testing.T) {
cfg := loadConfig(t, `
pipelines:
- id: reports
source:
backend: local
path: /source
destinations:
- id: archive
backend: local
path: /archive
state:
mode: single_owner
- id: web
backend: local
path: /web
state:
mode: shared_root
`)
destinations := cfg.Pipelines[0].Destinations
if got, want := destinations[0].State.Mode, StateModeSingleOwner; got != want {
t.Fatalf("archive state mode = %q, want %q", got, want)
}
if got, want := destinations[1].State.Mode, StateModeSharedRoot; got != want {
t.Fatalf("web state mode = %q, want %q", got, want)
if got, want := destinations[1].Workflow, WorkflowReplacement; got != want {
t.Fatalf("web workflow = %q, want %q", got, want)
}
}
@@ -852,8 +815,63 @@ pipelines:
`, "backend ftp is unsupported")
}
func TestLoadFileRejectsInvalidTransferAction(t *testing.T) {
func TestLoadFileRejectsInvalidWorkflow(t *testing.T) {
assertLoadError(t, `
pipelines:
- id: reports
source:
backend: local
path: /source
destinations:
- id: archive
backend: local
path: /archive
workflow: append
`, "workflow must be additive or replacement")
}
func TestLoadFileRejectsLegacyDestinationPolicyFields(t *testing.T) {
tests := map[string]string{
"state": `
pipelines:
- id: reports
source:
backend: local
path: /source
destinations:
- id: archive
backend: local
path: /archive
state:
mode: single_owner
`,
"reconciliation": `
pipelines:
- id: reports
source:
backend: local
path: /source
destinations:
- id: archive
backend: local
path: /archive
reconciliation:
mode: replace
`,
"takeover": `
pipelines:
- id: reports
source:
backend: local
path: /source
destinations:
- id: archive
backend: local
path: /archive
takeover:
mode: same_pipeline
`,
"transfer": `
pipelines:
- id: reports
source:
@@ -864,8 +882,14 @@ pipelines:
backend: local
path: /archive
transfer:
on_destination_older: overwrite
`, "on_destination_older must be replace or fail")
on_destination_older: replace
`,
}
for name, body := range tests {
t.Run(name, func(t *testing.T) {
assertLoadError(t, body, "field "+name+" not found")
})
}
}
func TestLoadFileRejectsInvalidValidationAction(t *testing.T) {
@@ -941,8 +965,6 @@ func TestExampleConfigsLoad(t *testing.T) {
"../../examples/local-index.yml",
"../../examples/fan-out.yml",
"../../examples/archive-and-latest.yml",
"../../examples/merge-reconciliation.yml",
"../../examples/shared-root.yml",
"../../examples/http-upload-local.yml",
"../../examples/ssh-destination.yml",
"../../examples/s3-destination.yml",

View File

@@ -2,8 +2,10 @@ package config
import (
"fmt"
"net/url"
"regexp"
"strings"
"unicode"
"gitea.maximumdirect.net/eric/distributor/internal/link"
)
@@ -72,10 +74,8 @@ func Validate(cfg Config) error {
errs = validatePublishTransformPolicy(errs, destinationContext, destination.Publish, destination.Transform)
errs = validatePathMapping(errs, destinationContext+".path_mapping", destination.PathMap)
errs = validateLinks(errs, destinationContext+".links", destination.Links)
errs = validateStatePolicy(errs, destinationContext+".state", destination.State)
errs = validateReconciliationPolicy(errs, destinationContext+".reconciliation", destination.Reconciliation)
errs = validateWorkflow(errs, destinationContext+".workflow", destination.Workflow)
errs = validateRetentionPolicy(errs, destinationContext+".retention", destination.Retention)
errs = validateTransferPolicy(errs, destinationContext+".transfer", destination.Transfer)
}
}
@@ -281,9 +281,15 @@ func ValidatePublishTransformPolicy(publish PublishPolicy, transform Transform)
if transform.MarkdownToHTML.Input != "" && !transform.MarkdownToHTML.Enabled {
return fmt.Errorf("transform.markdown_to_html.input requires transform.markdown_to_html.enabled to be true")
}
if transform.MarkdownToHTML.CssHref != "" && !transform.MarkdownToHTML.Enabled {
return fmt.Errorf("transform.markdown_to_html.css_href requires transform.markdown_to_html.enabled to be true")
}
if transform.MarkdownToHTML.Input != "" && mode != TransformModeIndex {
return fmt.Errorf("transform.markdown_to_html.input is only valid when mode is %s", TransformModeIndex)
}
if err := validateCSSHref(transform.MarkdownToHTML.CssHref); err != nil {
return fmt.Errorf("transform.markdown_to_html.css_href %w", err)
}
if transform.MarkdownToHTML.Enabled && !publish.HTML {
return fmt.Errorf("transform.markdown_to_html.enabled requires publish.html to be true")
}
@@ -293,6 +299,49 @@ func ValidatePublishTransformPolicy(publish PublishPolicy, transform Transform)
return nil
}
func validateCSSHref(value string) error {
if value == "" {
return nil
}
for _, character := range value {
if unicode.IsControl(character) || unicode.IsSpace(character) {
return fmt.Errorf("must not contain whitespace or control characters")
}
}
if strings.ContainsAny(value, "\\<>\"'") {
return fmt.Errorf("must not contain backslashes or HTML-sensitive characters")
}
if strings.HasPrefix(value, "//") {
return fmt.Errorf("must not be scheme-relative")
}
parsed, err := url.Parse(value)
if err != nil {
return fmt.Errorf("must be a valid URL reference: %w", err)
}
if parsed.Fragment != "" {
return fmt.Errorf("must not include a fragment")
}
if parsed.Scheme != "" {
if parsed.Scheme != "http" && parsed.Scheme != "https" {
return fmt.Errorf("scheme must be http or https")
}
if parsed.Host == "" {
return fmt.Errorf("host is required for absolute URLs")
}
if parsed.User != nil {
return fmt.Errorf("must not include userinfo")
}
return nil
}
if parsed.Host != "" {
return fmt.Errorf("must not be scheme-relative")
}
if parsed.Path == "" {
return fmt.Errorf("relative URL path is required")
}
return nil
}
func validatePathMapping(errs ValidationErrors, context string, mapping PathMapping) ValidationErrors {
if mapping.Mode != PathMappingPreserveRelative && mapping.Mode != PathMappingFixed {
errs = append(errs, context+".mode must be "+PathMappingPreserveRelative+" or "+PathMappingFixed)
@@ -317,9 +366,9 @@ func validateLinks(errs ValidationErrors, context string, links *Links) Validati
return errs
}
func validateReconciliationPolicy(errs ValidationErrors, context string, policy ReconciliationPolicy) ValidationErrors {
if policy.Mode != ReconciliationModeReplace && policy.Mode != ReconciliationModeMerge {
errs = append(errs, context+".mode must be "+ReconciliationModeReplace+" or "+ReconciliationModeMerge)
func validateWorkflow(errs ValidationErrors, context, workflow string) ValidationErrors {
if workflow != WorkflowAdditive && workflow != WorkflowReplacement {
errs = append(errs, context+" must be "+WorkflowAdditive+" or "+WorkflowReplacement)
}
return errs
}
@@ -340,26 +389,3 @@ func validateRetentionPolicy(errs ValidationErrors, context string, policy Reten
}
return errs
}
func validateStatePolicy(errs ValidationErrors, context string, policy StatePolicy) ValidationErrors {
if policy.Mode != StateModeSingleOwner && policy.Mode != StateModeSharedRoot {
errs = append(errs, context+".mode must be "+StateModeSingleOwner+" or "+StateModeSharedRoot)
}
return errs
}
func validateTransferPolicy(errs ValidationErrors, context string, policy TransferPolicy) ValidationErrors {
if policy.OnDestinationSame != TransferActionSkip && policy.OnDestinationSame != TransferActionFail {
errs = append(errs, context+".on_destination_same must be skip or fail")
}
if policy.OnDestinationOlder != TransferActionReplace && policy.OnDestinationOlder != TransferActionFail {
errs = append(errs, context+".on_destination_older must be replace or fail")
}
if policy.OnDestinationNewer != TransferActionSkip && policy.OnDestinationNewer != TransferActionFail && policy.OnDestinationNewer != TransferActionReplace {
errs = append(errs, context+".on_destination_newer must be skip, replace, or fail")
}
if policy.OnConflict != TransferActionFail && policy.OnConflict != TransferActionReplace {
errs = append(errs, context+".on_conflict must be fail or replace")
}
return errs
}

View File

@@ -51,29 +51,6 @@ func TestValidateChecksPublishTransformPolicy(t *testing.T) {
}
}
func TestValidateAcceptsForceReplacementTransferActions(t *testing.T) {
cfg := Config{Pipelines: []Pipeline{{
ID: "reports",
Source: Backend{
Backend: BackendLocal,
Path: "/source",
},
Destinations: []Destination{{
ID: "archive",
Backend: BackendLocal,
Path: "/destination",
Transfer: TransferPolicy{
OnDestinationNewer: TransferActionReplace,
OnConflict: TransferActionReplace,
},
}},
}}}
ApplyDefaults(&cfg)
if err := Validate(cfg); err != nil {
t.Fatalf("Validate() error = %v", err)
}
}
func TestValidatePathMapping(t *testing.T) {
tests := []struct {
name string
@@ -108,15 +85,15 @@ func TestValidatePathMapping(t *testing.T) {
}
}
func TestValidateReconciliationPolicy(t *testing.T) {
func TestValidateWorkflow(t *testing.T) {
tests := []struct {
name string
mode string
workflow string
wantErr bool
}{
{name: "replace", mode: ReconciliationModeReplace},
{name: "merge", mode: ReconciliationModeMerge},
{name: "invalid", mode: "append", wantErr: true},
{name: "additive", workflow: WorkflowAdditive},
{name: "replacement", workflow: WorkflowReplacement},
{name: "invalid", workflow: "append", wantErr: true},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
@@ -127,7 +104,7 @@ func TestValidateReconciliationPolicy(t *testing.T) {
ID: "archive",
Backend: BackendLocal,
Path: "/destination",
Reconciliation: ReconciliationPolicy{Mode: tt.mode},
Workflow: tt.workflow,
}},
}}}
ApplyDefaults(&cfg)
@@ -142,18 +119,7 @@ func TestValidateReconciliationPolicy(t *testing.T) {
}
}
func TestValidateStatePolicy(t *testing.T) {
tests := []struct {
name string
mode string
wantErr bool
}{
{name: "single owner", mode: StateModeSingleOwner},
{name: "shared root", mode: StateModeSharedRoot},
{name: "invalid", mode: "shared", wantErr: true},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
func TestValidateWorkflowReportsFieldContext(t *testing.T) {
cfg := Config{Pipelines: []Pipeline{{
ID: "reports",
Source: Backend{Backend: BackendLocal, Path: "/source"},
@@ -161,18 +127,17 @@ func TestValidateStatePolicy(t *testing.T) {
ID: "archive",
Backend: BackendLocal,
Path: "/destination",
State: StatePolicy{Mode: tt.mode},
Workflow: "append",
}},
}}}
ApplyDefaults(&cfg)
err := Validate(cfg)
if tt.wantErr && err == nil {
if err == nil {
t.Fatal("Validate() error = nil, want error")
}
if !tt.wantErr && err != nil {
t.Fatalf("Validate() error = %v", err)
}
})
want := "pipelines[0].destinations[0].workflow must be additive or replacement"
if !strings.Contains(err.Error(), want) {
t.Fatalf("Validate() error = %q, want %q", err, want)
}
}
@@ -328,6 +293,24 @@ func publishTransformPolicyCases() []publishTransformPolicyCase {
Input: "report.md",
}},
},
{
name: "html only sidecar css href allowed",
publish: PublishPolicy{HTML: true},
transform: Transform{MarkdownToHTML: &MarkdownToHTML{
Enabled: true,
Mode: TransformModeSidecar,
CssHref: "/assets/report.css",
}},
},
{
name: "html only index css href allowed",
publish: PublishPolicy{HTML: true},
transform: Transform{MarkdownToHTML: &MarkdownToHTML{
Enabled: true,
Mode: TransformModeIndex,
CssHref: "assets/report.css?v=20260614",
}},
},
{
name: "source and html sidecar allowed",
publish: PublishPolicy{Source: true, HTML: true},
@@ -425,6 +408,16 @@ func publishTransformPolicyCases() []publishTransformPolicyCase {
}},
wantErr: true,
},
{
name: "disabled markdown css href rejected",
publish: PublishPolicy{Source: true},
transform: Transform{MarkdownToHTML: &MarkdownToHTML{
Enabled: false,
Mode: TransformModeSidecar,
CssHref: "/assets/report.css",
}},
wantErr: true,
},
{
name: "disabled markdown wrong mode rejected",
publish: PublishPolicy{Source: true},
@@ -436,3 +429,44 @@ func publishTransformPolicyCases() []publishTransformPolicyCase {
},
}
}
func TestValidateCSSHref(t *testing.T) {
tests := []struct {
name string
value string
wantErr bool
}{
{name: "empty"},
{name: "root relative", value: "/assets/report.css"},
{name: "relative", value: "assets/report.css"},
{name: "parent relative", value: "../assets/report.css"},
{name: "query", value: "/assets/report.css?v=20260614"},
{name: "http", value: "http://example.com/report.css"},
{name: "https", value: "https://example.com/assets/report.css?v=1"},
{name: "javascript", value: "javascript:alert(1)", wantErr: true},
{name: "data", value: "data:text/css,body{}", wantErr: true},
{name: "file", value: "file:///tmp/report.css", wantErr: true},
{name: "scheme relative", value: "//example.com/report.css", wantErr: true},
{name: "userinfo", value: "https://user@example.com/report.css", wantErr: true},
{name: "fragment", value: "/assets/report.css#main", wantErr: true},
{name: "space", value: "/assets/report css", wantErr: true},
{name: "tab", value: "/assets/report\tcss", wantErr: true},
{name: "newline", value: "/assets/report\ncss", wantErr: true},
{name: "backslash", value: `assets\report.css`, wantErr: true},
{name: "less than", value: "/assets/<report>.css", wantErr: true},
{name: "double quote", value: `/assets/"report".css`, wantErr: true},
{name: "single quote", value: "/assets/'report'.css", wantErr: true},
{name: "query only", value: "?v=1", wantErr: true},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
err := validateCSSHref(tt.value)
if tt.wantErr && err == nil {
t.Fatal("validateCSSHref() error = nil, want error")
}
if !tt.wantErr && err != nil {
t.Fatalf("validateCSSHref() error = %v", err)
}
})
}
}

View File

@@ -4,6 +4,7 @@ import (
"context"
"encoding/json"
"fmt"
"sort"
"time"
"gitea.maximumdirect.net/eric/distributor/internal/config"
@@ -16,7 +17,9 @@ func Execute(ctx context.Context, req Request, plan Plan) error {
switch plan.Action {
case ActionSkipSame, ActionSkipDestinationNewer:
return nil
case ActionPublishNew, ActionReplaceOlder, ActionForceReplace:
case ActionPublishNew, ActionUpsertAdditive, ActionReplaceCatalog:
return executeCatalog(ctx, req, plan)
case ActionReplaceOlder, ActionReplaceConflict, ActionReplaceNewer, ActionReplaceTakeover, ActionForceReplace:
if usesSharedRootState(req, plan) {
return executeSharedRoot(ctx, req, plan)
}
@@ -24,11 +27,11 @@ func Execute(ctx context.Context, req Request, plan Plan) error {
return fmt.Errorf("cannot execute action %s: %s", plan.Action, plan.Reason)
}
if plan.Action == ActionReplaceOlder {
if plan.Action == ActionReplaceOlder || plan.Action == ActionReplaceConflict || plan.Action == ActionReplaceNewer || plan.Action == ActionReplaceTakeover {
if plan.ExistingState == nil {
return fmt.Errorf("replace requires existing destination state")
}
if plan.Reconciliation.Mode == config.ReconciliationModeReplace {
if plan.Reconciliation.Mode == config.ReconciliationModeReplace || plan.Action == ActionReplaceConflict || plan.Action == ActionReplaceTakeover {
if err := req.DestinationBackend.DeleteManagedBundle(ctx, req.DestinationBundlePath, state.ManagedOutputPaths(*plan.ExistingState), storage.DeleteOptions{IgnoreMissing: true, PruneEmptyDirs: true}); err != nil {
return err
}
@@ -138,6 +141,152 @@ func Execute(ctx context.Context, req Request, plan Plan) error {
return nil
}
func executeCatalog(ctx context.Context, req Request, plan Plan) error {
if plan.Action == ActionReplaceCatalog {
if plan.ClearDestinationRoot {
if err := req.DestinationBackend.DeletePrefix(ctx, req.DestinationBundlePath, storage.DeleteOptions{IgnoreMissing: true, PruneEmptyDirs: true}); err != nil {
return err
}
if err := ensureDestinationEmpty(ctx, req.DestinationBackend, req.DestinationBundlePath); err != nil {
return err
}
} else if len(plan.CatalogOutputsToDelete) > 0 {
if err := req.DestinationBackend.DeleteManagedOutputs(ctx, req.DestinationBundlePath, catalogOutputPaths(plan.CatalogOutputsToDelete), storage.DeleteOptions{IgnoreMissing: true, PruneEmptyDirs: true}); err != nil {
return err
}
}
}
writtenOutputs := make([]Output, 0, len(plan.Outputs))
newOutputs := make([]Output, 0, len(plan.Outputs))
cleanup := func() {
outputs := writtenOutputs
if plan.Action == ActionUpsertAdditive {
outputs = newOutputs
}
_ = req.DestinationBackend.DeleteManagedOutputs(ctx, req.DestinationBundlePath, ManagedOutputPaths(outputs), storage.DeleteOptions{IgnoreMissing: true, PruneEmptyDirs: true})
}
for _, output := range plan.Outputs {
destinationPath, err := storage.Join(req.DestinationBundlePath, output.DestinationPath)
if err != nil {
cleanup()
return err
}
created, err := catalogWriteCreatesOutput(ctx, req.DestinationBackend, destinationPath)
if err != nil {
cleanup()
return err
}
data := output.Data
if output.Kind == state.OutputKindSource {
sourcePath, err := storage.Join(req.SourceBundle.RootRelativePath, output.SourcePath)
if err != nil {
cleanup()
return err
}
data, err = req.SourceBackend.ReadFile(ctx, sourcePath)
if err != nil {
cleanup()
return err
}
}
if _, err := req.DestinationBackend.WriteFile(ctx, destinationPath, data, storage.WriteOptions{Overwrite: catalogOutputOverwriteAllowed(plan, output), PreferAtomic: true}); err != nil {
cleanup()
return err
}
writtenOutputs = append(writtenOutputs, output)
if created {
newOutputs = append(newOutputs, output)
}
}
catalogState := catalogStateForPlan(req, plan)
if err := state.ValidateCatalog(catalogState); err != nil {
cleanup()
return err
}
data, err := json.MarshalIndent(catalogState, "", " ")
if err != nil {
cleanup()
return err
}
data = append(data, '\n')
statePath, err := storage.StatePath(req.DestinationBundlePath)
if err != nil {
cleanup()
return err
}
if _, err := req.DestinationBackend.WriteFile(ctx, statePath, data, storage.WriteOptions{Overwrite: catalogStateWriteOverwrites(plan), PreferAtomic: true}); err != nil {
cleanup()
return err
}
return nil
}
func catalogWriteCreatesOutput(ctx context.Context, backend storage.Backend, destinationPath string) (bool, error) {
if _, err := backend.Stat(ctx, destinationPath); err == nil {
return false, nil
} else if storage.IsNotFound(err) {
return true, nil
} else {
return false, err
}
}
func catalogOutputOverwriteAllowed(plan Plan, output Output) bool {
if plan.ClearDestinationRoot {
return false
}
if plan.SupersededLegacy != nil {
return true
}
if plan.ExistingCatalog == nil {
return false
}
_, ok := state.FindCatalogOutputByPath(plan.ExistingCatalog.Outputs, output.DestinationPath)
return ok
}
func catalogStateForPlan(req Request, plan Plan) state.CatalogState {
now := requestTime(req)
createdAt := now
if plan.ExistingCatalog != nil {
createdAt = plan.ExistingCatalog.CreatedAt
}
outputs := make([]state.CatalogOutputFile, 0, len(plan.CatalogOutputsToRetain)+len(plan.CatalogOutputsToWrite))
outputs = append(outputs, plan.CatalogOutputsToRetain...)
outputs = append(outputs, plan.CatalogOutputsToWrite...)
sort.SliceStable(outputs, func(i, j int) bool {
if outputs[i].Path != outputs[j].Path {
return outputs[i].Path < outputs[j].Path
}
if outputs[i].PipelineID != outputs[j].PipelineID {
return outputs[i].PipelineID < outputs[j].PipelineID
}
return outputs[i].DestinationID < outputs[j].DestinationID
})
return state.CatalogState{
SchemaVersion: state.CatalogSchemaVersion,
DistributorVersion: req.DistributorVersion,
CreatedAt: createdAt,
UpdatedAt: now,
State: state.StatePolicy{Mode: state.StateModeCatalog},
Outputs: outputs,
}
}
func catalogStateWriteOverwrites(plan Plan) bool {
return plan.ExistingCatalog != nil || plan.SupersededLegacy != nil
}
func catalogOutputPaths(outputs []state.CatalogOutputFile) []string {
paths := make([]string, 0, len(outputs))
for _, output := range outputs {
paths = append(paths, output.Path)
}
return paths
}
func executeSharedRoot(ctx context.Context, req Request, plan Plan) error {
plan.Reconciliation = normalizeReconciliation(plan.Reconciliation)
if plan.Action == ActionForceReplace {
@@ -148,7 +297,7 @@ func executeSharedRoot(ctx context.Context, req Request, plan Plan) error {
return err
}
}
if plan.Action == ActionReplaceOlder && plan.Reconciliation.Mode == config.ReconciliationModeReplace {
if plan.Action == ActionReplaceTakeover || plan.Action == ActionReplaceConflict || (isReconciliationReplacementAction(plan.Action) && plan.Reconciliation.Mode == config.ReconciliationModeReplace) {
if err := req.DestinationBackend.DeleteManagedOutputs(ctx, req.DestinationBundlePath, sharedRootOutputPaths(plan.OwnerOutputsToDelete), storage.DeleteOptions{IgnoreMissing: true, PruneEmptyDirs: true}); err != nil {
return err
}
@@ -158,7 +307,7 @@ func executeSharedRoot(ctx context.Context, req Request, plan Plan) error {
newOutputs := make([]Output, 0, len(plan.Outputs))
cleanup := func() {
outputs := writtenOutputs
if plan.Reconciliation.Mode == config.ReconciliationModeMerge {
if isReconciliationReplacementAction(plan.Action) && plan.Reconciliation.Mode == config.ReconciliationModeMerge {
outputs = newOutputs
}
_ = req.DestinationBackend.DeleteManagedOutputs(ctx, req.DestinationBundlePath, ManagedOutputPaths(outputs), storage.DeleteOptions{IgnoreMissing: true, PruneEmptyDirs: true})
@@ -240,7 +389,7 @@ func ensureMergeOutputPaths(ctx context.Context, backend storage.Backend, bundle
}
func usesSharedRootState(req Request, plan Plan) bool {
return normalizeState(req.State).Mode == config.StateModeSharedRoot || plan.StateMode == config.StateModeSharedRoot
return plan.StateMode == config.StateModeSharedRoot
}
func outputManagedByExistingState(output Output, existing *state.DistributorState) bool {
@@ -257,6 +406,11 @@ func outputManagedBySharedRootPlan(output Output, plan Plan) bool {
return true
}
}
for _, existing := range plan.TakenOverOwnerOutputs {
if existing.Path == output.DestinationPath {
return true
}
}
return false
}
@@ -273,7 +427,7 @@ func stateOutputsForPlan(plan Plan, now time.Time) ([]state.OutputFile, error) {
}
func usesMergeRetention(plan Plan) bool {
return plan.Reconciliation.Mode == config.ReconciliationModeMerge && plan.Action == ActionReplaceOlder
return plan.Reconciliation.Mode == config.ReconciliationModeMerge && isReconciliationReplacementAction(plan.Action)
}
func sharedRootStateForPlan(req Request, plan Plan, now time.Time) (state.SharedRootState, error) {
@@ -283,6 +437,7 @@ func sharedRootStateForPlan(req Request, plan Plan, now time.Time) (state.Shared
scope = state.CurrentOwnerScope(req.PipelineID, req.DestinationID)
}
base := sharedRootBaseState(req, plan, now)
base = removeTakenOverSharedRootOutputs(base, plan.TakenOverOwnerOutputs)
owner := state.OwnerRecord{
Scope: scope,
Reconciliation: state.ReconciliationPolicy{Mode: plan.Reconciliation.Mode},
@@ -292,7 +447,7 @@ func sharedRootStateForPlan(req Request, plan Plan, now time.Time) (state.Shared
owner.Links = &state.LinkState{PrimaryURL: plan.PrimaryURL}
}
planned := state.ProjectSharedRootOutputs(StateOutputProjections(plan.Outputs), currentOwnerSharedRootOutputs(plan), scope, req.SourceBundle.Manifest, now)
if plan.Action == ActionReplaceOlder && plan.Reconciliation.Mode == config.ReconciliationModeMerge {
if isReconciliationReplacementAction(plan.Action) && plan.Reconciliation.Mode == config.ReconciliationModeMerge {
return state.MergeOwnerOutputs(base, scope, owner, planned)
}
return state.ReplaceOwnerOutputs(base, scope, owner, planned)
@@ -319,6 +474,22 @@ func sharedRootBaseState(req Request, plan Plan, now time.Time) state.SharedRoot
return newSharedRootState(req, now)
}
func removeTakenOverSharedRootOutputs(sharedRoot state.SharedRootState, takenOver []state.SharedRootOutputFile) state.SharedRootState {
if len(takenOver) == 0 {
return sharedRoot
}
paths := sharedRootOutputPathSet(takenOver)
next := sharedRoot
next.Outputs = make([]state.SharedRootOutputFile, 0, len(sharedRoot.Outputs))
for _, output := range sharedRoot.Outputs {
if _, remove := paths[output.Path]; remove {
continue
}
next.Outputs = append(next.Outputs, output)
}
return next
}
func newSharedRootState(req Request, now time.Time) state.SharedRootState {
return state.SharedRootState{
SchemaVersion: state.SharedRootSchemaVersion,

View File

@@ -2,356 +2,167 @@ package publish
import (
"context"
"fmt"
"io"
"testing"
"time"
"gitea.maximumdirect.net/eric/distributor/internal/bundle"
"gitea.maximumdirect.net/eric/distributor/internal/config"
"gitea.maximumdirect.net/eric/distributor/internal/state"
"gitea.maximumdirect.net/eric/distributor/internal/storage"
"gitea.maximumdirect.net/eric/distributor/internal/storage/fake"
"gitea.maximumdirect.net/eric/distributor/internal/testutil"
"gitea.maximumdirect.net/eric/distributor/internal/transform"
)
func TestExecuteCleansUpAfterWriteFailure(t *testing.T) {
sourceBackend := fake.New()
destinationBackend := &failingBackend{Backend: fake.New(), failPath: "summary.txt"}
sourceBundle := testutil.WriteFakeSourceBundle(t, sourceBackend, "", testutil.BundleOptions{})
req := Request{
PipelineID: "reports",
DestinationID: "archive",
SourceBundle: sourceBundle,
SourceBackend: sourceBackend,
DestinationBackend: destinationBackend,
DestinationBundlePath: "",
Publish: config.PublishPolicy{Source: true},
Transfer: config.TransferPolicy{OnDestinationSame: config.TransferActionSkip, OnDestinationOlder: config.TransferActionReplace, OnDestinationNewer: config.TransferActionSkip, OnConflict: config.TransferActionFail},
DistributorVersion: "test",
func TestExecuteAdditiveWritesOutputsAndCatalog(t *testing.T) {
_, destinationBackend, req := catalogPlanRequest(t, config.WorkflowAdditive)
existing := baseCatalog(req)
existing.Outputs = []state.CatalogOutputFile{
catalogOutput(req, "reports", "archive", "report.md", state.OutputKindSource, planCreatedAt),
catalogOutput(req, "reports", "web", "old.txt", state.OutputKindSource, planCreatedAt),
}
writeCatalogState(t, destinationBackend, "", existing)
testutil.WriteFakeFile(t, destinationBackend, "report.md", "old report")
testutil.WriteFakeFile(t, destinationBackend, "old.txt", "retained")
plan, err := Build(context.Background(), req)
if err != nil {
t.Fatalf("Build() error = %v", err)
}
if err := Execute(context.Background(), req, plan); err != nil {
t.Fatalf("Execute() error = %v", err)
}
testutil.AssertFakeFile(t, destinationBackend, "report.md", "# Report\nSunny.\n")
testutil.AssertFakeFile(t, destinationBackend, "summary.txt", "Summary\n")
testutil.AssertFakeFile(t, destinationBackend, "old.txt", "retained")
catalog := readCatalogState(t, destinationBackend, "")
if catalog.SchemaVersion != state.CatalogSchemaVersion || catalog.State.Mode != state.StateModeCatalog {
t.Fatalf("catalog identity = schema %d mode %s", catalog.SchemaVersion, catalog.State.Mode)
}
if len(catalog.Outputs) != 3 {
t.Fatalf("catalog outputs = %#v, want three outputs", catalog.Outputs)
}
report, ok := state.FindCatalogOutputByPath(catalog.Outputs, "report.md")
if !ok {
t.Fatalf("catalog outputs = %#v, want report.md", catalog.Outputs)
}
if !report.CreatedAt.Equal(planCreatedAt) || !report.UpdatedAt.Equal(planUpdatedAt) {
t.Fatalf("report times = %s/%s, want created preserved and updated now", report.CreatedAt, report.UpdatedAt)
}
if report.SourcePath != "" {
t.Fatalf("source catalog output source_path = %q, want empty", report.SourcePath)
}
}
func TestExecuteReplacementDeletesCurrentOwnerAndPreservesOtherOwners(t *testing.T) {
_, destinationBackend, req := catalogPlanRequest(t, config.WorkflowReplacement)
existing := baseCatalog(req)
existing.Outputs = []state.CatalogOutputFile{
catalogOutput(req, "reports", "archive", "report.md", state.OutputKindSource, planCreatedAt),
catalogOutput(req, "reports", "archive", "stale.txt", state.OutputKindSource, planCreatedAt),
catalogOutput(req, "reports", "web", "shared.txt", state.OutputKindSource, planCreatedAt),
}
writeCatalogState(t, destinationBackend, "", existing)
testutil.WriteFakeFile(t, destinationBackend, "report.md", "old report")
testutil.WriteFakeFile(t, destinationBackend, "stale.txt", "delete me")
testutil.WriteFakeFile(t, destinationBackend, "shared.txt", "keep me")
plan, err := Build(context.Background(), req)
if err != nil {
t.Fatalf("Build() error = %v", err)
}
if err := Execute(context.Background(), req, plan); err != nil {
t.Fatalf("Execute() error = %v", err)
}
testutil.AssertFakeFile(t, destinationBackend, "report.md", "# Report\nSunny.\n")
testutil.AssertFakeFile(t, destinationBackend, "summary.txt", "Summary\n")
testutil.AssertFakeMissing(t, destinationBackend, "stale.txt")
testutil.AssertFakeFile(t, destinationBackend, "shared.txt", "keep me")
catalog := readCatalogState(t, destinationBackend, "")
if _, ok := state.FindCatalogOutputByPath(catalog.Outputs, "stale.txt"); ok {
t.Fatalf("catalog outputs = %#v, want stale.txt removed", catalog.Outputs)
}
if _, ok := state.FindCatalogOutputByPath(catalog.Outputs, "shared.txt"); !ok {
t.Fatalf("catalog outputs = %#v, want shared.txt retained", catalog.Outputs)
}
}
func TestExecuteSupersededReplacementClearsDestinationRootOnly(t *testing.T) {
_, destinationBackend, req := catalogPlanRequest(t, config.WorkflowReplacement)
req.DestinationBundlePath = "bundle"
legacyState := testutil.DestinationState(req.SourceBundle.Manifest, testutil.DestinationStateOptions{})
writeJSONState(t, destinationBackend, req.DestinationBundlePath, legacyState)
testutil.WriteFakeFile(t, destinationBackend, "bundle/unplanned.txt", "remove")
testutil.WriteFakeFile(t, destinationBackend, "outside.txt", "keep")
plan, err := Build(context.Background(), req)
if err != nil {
t.Fatalf("Build() error = %v", err)
}
if err := Execute(context.Background(), req, plan); err != nil {
t.Fatalf("Execute() error = %v", err)
}
testutil.AssertFakeMissing(t, destinationBackend, "bundle/unplanned.txt")
testutil.AssertFakeFile(t, destinationBackend, "bundle/report.md", "# Report\nSunny.\n")
testutil.AssertFakeFile(t, destinationBackend, "outside.txt", "keep")
readCatalogState(t, destinationBackend, "bundle")
}
func TestExecuteSupersededAdditiveLeavesUnplannedFilesUnmanaged(t *testing.T) {
_, destinationBackend, req := catalogPlanRequest(t, config.WorkflowAdditive)
legacyState := testutil.DestinationState(req.SourceBundle.Manifest, testutil.DestinationStateOptions{})
writeJSONState(t, destinationBackend, "", legacyState)
testutil.WriteFakeFile(t, destinationBackend, "report.md", "legacy report")
testutil.WriteFakeFile(t, destinationBackend, "unplanned.txt", "leave me")
plan, err := Build(context.Background(), req)
if err != nil {
t.Fatalf("Build() error = %v", err)
}
if err := Execute(context.Background(), req, plan); err != nil {
t.Fatalf("Execute() error = %v", err)
}
testutil.AssertFakeFile(t, destinationBackend, "report.md", "# Report\nSunny.\n")
testutil.AssertFakeFile(t, destinationBackend, "unplanned.txt", "leave me")
catalog := readCatalogState(t, destinationBackend, "")
if _, ok := state.FindCatalogOutputByPath(catalog.Outputs, "unplanned.txt"); ok {
t.Fatalf("catalog outputs = %#v, want unplanned file omitted", catalog.Outputs)
}
}
func TestExecuteFailedWriteDoesNotWriteCatalogState(t *testing.T) {
_, destinationBackend, req := catalogPlanRequest(t, config.WorkflowAdditive)
plan, err := Build(context.Background(), req)
if err != nil {
t.Fatalf("Build() error = %v", err)
}
if err := destinationBackend.AddDirectory("report.md"); err != nil {
t.Fatalf("add conflicting directory: %v", err)
}
err = Execute(context.Background(), req, plan)
if err == nil {
t.Fatal("Execute() error = nil, want error")
t.Fatal("Execute() error = nil, want write failure")
}
found, err := destinationBackend.HasAny(context.Background(), "")
if err != nil {
t.Fatalf("HasAny() error = %v", err)
}
if found {
t.Fatal("destination has content after failed execution")
if _, statErr := destinationBackend.Stat(context.Background(), storage.StateFileName); !storage.IsNotFound(statErr) {
t.Fatalf("state stat error = %v, want missing state", statErr)
}
}
func TestExecuteReplaceDeletesOmittedManagedOutputs(t *testing.T) {
sourceBackend := fake.New()
sourceBundle := testutil.WriteFakeSourceBundle(t, sourceBackend, "", testutil.BundleOptions{
Files: []testutil.SourceFile{{Path: "report.md", Data: "# Report\nNew.\n"}},
})
destinationBackend := fake.New()
older := sourceBundle.Manifest
older.Created = older.Created.Add(-time.Hour)
older.Files = append([]bundle.ManifestFile(nil), testutil.ValidManifest(testutil.BundleOptions{}).Files...)
older.Digest = bundle.BundleDigest(older.Files)
testutil.WriteFakeDestinationState(t, destinationBackend, "", older, testutil.DestinationStateOptions{})
req := testRequest(sourceBackend, destinationBackend, sourceBundle, config.ReconciliationModeReplace)
plan, err := Build(context.Background(), req)
if err != nil {
t.Fatalf("Build() error = %v", err)
}
if plan.Action != ActionReplaceOlder {
t.Fatalf("plan action = %s, want replace_older", plan.Action)
}
if err := Execute(context.Background(), req, plan); err != nil {
t.Fatalf("Execute() error = %v", err)
}
testutil.AssertFakeFile(t, destinationBackend, "report.md", "# Report\nNew.\n")
testutil.AssertFakeMissing(t, destinationBackend, "summary.txt")
destinationState := readFakeState(t, destinationBackend, "")
if got, want := len(destinationState.Outputs), 1; got != want {
t.Fatalf("state output count = %d, want %d", got, want)
}
if got, want := destinationState.Reconciliation.Mode, config.ReconciliationModeReplace; got != want {
t.Fatalf("reconciliation mode = %q, want %q", got, want)
}
}
func TestExecuteMergeRetainsOmittedAndOverwritesManagedOutputs(t *testing.T) {
sourceBackend := fake.New()
sourceBundle := testutil.WriteFakeSourceBundle(t, sourceBackend, "", testutil.BundleOptions{
Files: []testutil.SourceFile{{Path: "report.md", Data: "# Report\nNew.\n"}},
})
destinationBackend := fake.New()
older := sourceBundle.Manifest
older.Created = older.Created.Add(-time.Hour)
older.Files = append([]bundle.ManifestFile(nil), testutil.ValidManifest(testutil.BundleOptions{}).Files...)
older.Digest = bundle.BundleDigest(older.Files)
existingState := testutil.WriteFakeDestinationState(t, destinationBackend, "", older, testutil.DestinationStateOptions{})
req := testRequest(sourceBackend, destinationBackend, sourceBundle, config.ReconciliationModeMerge)
plan, err := Build(context.Background(), req)
if err != nil {
t.Fatalf("Build() error = %v", err)
}
if err := Execute(context.Background(), req, plan); err != nil {
t.Fatalf("Execute() error = %v", err)
}
testutil.AssertFakeFile(t, destinationBackend, "report.md", "# Report\nNew.\n")
testutil.AssertFakeFile(t, destinationBackend, "summary.txt", "old")
destinationState := readFakeState(t, destinationBackend, "")
outputs := outputsByPath(destinationState.Outputs)
if got, want := len(outputs), 2; got != want {
t.Fatalf("state output count = %d, want %d", got, want)
}
if !outputs["summary.txt"].CreatedAt.Equal(existingState.Outputs[1].CreatedAt) || !outputs["summary.txt"].UpdatedAt.Equal(existingState.Outputs[1].UpdatedAt) {
t.Fatalf("retained output timestamps = %#v, want existing %#v", outputs["summary.txt"], existingState.Outputs[1])
}
if !outputs["report.md"].CreatedAt.Equal(existingState.Outputs[0].CreatedAt) || !outputs["report.md"].UpdatedAt.After(existingState.Outputs[0].UpdatedAt) {
t.Fatalf("updated output timestamps = %#v, want preserved created_at and newer updated_at", outputs["report.md"])
}
if got, want := destinationState.Reconciliation.Mode, config.ReconciliationModeMerge; got != want {
t.Fatalf("reconciliation mode = %q, want %q", got, want)
}
}
func TestExecuteMergeFailsOnUnmanagedDestinationPathCollision(t *testing.T) {
sourceBackend := fake.New()
sourceBundle := testutil.WriteFakeSourceBundle(t, sourceBackend, "", testutil.BundleOptions{
Files: []testutil.SourceFile{{Path: "report.md", Data: "# Report\nNew.\n"}},
})
destinationBackend := fake.New()
older := sourceBundle.Manifest
older.Created = older.Created.Add(-time.Hour)
older.Files = []bundle.ManifestFile{{
Path: "summary.txt",
SHA256: bundle.FileDigest([]byte("Summary\n")),
Size: int64(len("Summary\n")),
}}
older.Digest = bundle.BundleDigest(older.Files)
testutil.WriteFakeDestinationState(t, destinationBackend, "", older, testutil.DestinationStateOptions{})
testutil.WriteFakeFile(t, destinationBackend, "report.md", "unmanaged")
req := testRequest(sourceBackend, destinationBackend, sourceBundle, config.ReconciliationModeMerge)
plan, err := Build(context.Background(), req)
if err != nil {
t.Fatalf("Build() error = %v", err)
}
err = Execute(context.Background(), req, plan)
if err == nil {
t.Fatal("Execute() error = nil, want unmanaged path collision")
}
testutil.AssertFakeFile(t, destinationBackend, "report.md", "unmanaged")
testutil.AssertFakeFile(t, destinationBackend, "summary.txt", "old")
}
func TestExecuteMergeFailureCleansUpOnlyNewOutputs(t *testing.T) {
sourceBackend := fake.New()
sourceBundle := testutil.WriteFakeSourceBundle(t, sourceBackend, "", testutil.BundleOptions{
Files: []testutil.SourceFile{
{Path: "report.md", Data: "# Report\nNew.\n"},
{Path: "new.md", Data: "new\n"},
{Path: "fail.md", Data: "fail\n"},
},
})
destinationBackend := &failingBackend{Backend: fake.New(), failPath: "fail.md"}
older := sourceBundle.Manifest
older.Created = older.Created.Add(-time.Hour)
older.Files = []bundle.ManifestFile{sourceBundle.Manifest.Files[0]}
older.Digest = bundle.BundleDigest(older.Files)
testutil.WriteFakeDestinationState(t, destinationBackend.Backend, "", older, testutil.DestinationStateOptions{})
req := testRequest(sourceBackend, destinationBackend, sourceBundle, config.ReconciliationModeMerge)
plan, err := Build(context.Background(), req)
if err != nil {
t.Fatalf("Build() error = %v", err)
}
err = Execute(context.Background(), req, plan)
if err == nil {
t.Fatal("Execute() error = nil, want injected failure")
}
testutil.AssertFakeFile(t, destinationBackend.Backend, "report.md", "# Report\nNew.\n")
testutil.AssertFakeMissing(t, destinationBackend.Backend, "new.md")
testutil.AssertFakeMissing(t, destinationBackend.Backend, "fail.md")
}
func TestExecuteFixedPathSupportsReconciliationModes(t *testing.T) {
for _, mode := range []string{config.ReconciliationModeReplace, config.ReconciliationModeMerge} {
t.Run(mode, func(t *testing.T) {
sourceBackend := fake.New()
sourceBundle := testutil.WriteFakeSourceBundle(t, sourceBackend, "new", testutil.BundleOptions{
Files: []testutil.SourceFile{{Path: "report.md", Data: "# Report\nNew.\n"}},
})
destinationBackend := fake.New()
older := sourceBundle.Manifest
older.ID = "older.source"
older.Created = older.Created.Add(-time.Hour)
testutil.WriteFakeDestinationState(t, destinationBackend, "", older, testutil.DestinationStateOptions{})
req := testRequest(sourceBackend, destinationBackend, sourceBundle, mode)
req.DestinationBundlePath = ""
req.PathMapping = config.PathMappingFixed
plan, err := Build(context.Background(), req)
if err != nil {
t.Fatalf("Build() error = %v", err)
}
if plan.Action != ActionReplaceOlder {
t.Fatalf("plan action = %s, want replace_older", plan.Action)
}
if err := Execute(context.Background(), req, plan); err != nil {
t.Fatalf("Execute() error = %v", err)
}
testutil.AssertFakeFile(t, destinationBackend, "report.md", "# Report\nNew.\n")
destinationState := readFakeState(t, destinationBackend, "")
if got, want := destinationState.Reconciliation.Mode, mode; got != want {
t.Fatalf("state reconciliation mode = %q, want %q", got, want)
}
})
}
}
func TestExecuteReconciliationModesHonorPublishPolicies(t *testing.T) {
tests := []struct {
name string
publish config.PublishPolicy
transform config.Transform
transformer TransformerResolver
wantPaths []string
}{
{
name: "source only",
publish: config.PublishPolicy{Source: true},
wantPaths: []string{"report.md"},
},
{
name: "generated only",
publish: config.PublishPolicy{HTML: true},
transform: config.Transform{MarkdownToHTML: &config.MarkdownToHTML{Enabled: true, Mode: config.TransformModeSidecar}},
transformer: testResolver{transform.MarkdownToHTML: testTransformer{outputs: []transform.Output{{
Path: "report.html",
SourcePath: "report.md",
Transform: transform.MarkdownToHTML,
Data: []byte("<h1>Report</h1>\n"),
SHA256: bundle.FileDigest([]byte("<h1>Report</h1>\n")),
Size: int64(len("<h1>Report</h1>\n")),
}}}},
wantPaths: []string{"report.html"},
},
{
name: "source and generated",
publish: config.PublishPolicy{Source: true, HTML: true},
transform: config.Transform{MarkdownToHTML: &config.MarkdownToHTML{Enabled: true, Mode: config.TransformModeSidecar}},
transformer: testResolver{transform.MarkdownToHTML: testTransformer{outputs: []transform.Output{{
Path: "report.html",
SourcePath: "report.md",
Transform: transform.MarkdownToHTML,
Data: []byte("<h1>Report</h1>\n"),
SHA256: bundle.FileDigest([]byte("<h1>Report</h1>\n")),
Size: int64(len("<h1>Report</h1>\n")),
}}}},
wantPaths: []string{"report.md", "report.html"},
},
}
for _, mode := range []string{config.ReconciliationModeReplace, config.ReconciliationModeMerge} {
for _, tt := range tests {
t.Run(mode+" "+tt.name, func(t *testing.T) {
sourceBackend := fake.New()
sourceBundle := testutil.WriteFakeSourceBundle(t, sourceBackend, "", testutil.BundleOptions{
Files: []testutil.SourceFile{{Path: "report.md", Data: "# Report\nNew.\n"}},
})
destinationBackend := fake.New()
older := sourceBundle.Manifest
older.Created = older.Created.Add(-time.Hour)
testutil.WriteFakeDestinationState(t, destinationBackend, "", older, testutil.DestinationStateOptions{})
req := testRequest(sourceBackend, destinationBackend, sourceBundle, mode)
req.Publish = tt.publish
req.Transform = tt.transform
req.Transformers = tt.transformer
plan, err := Build(context.Background(), req)
if err != nil {
t.Fatalf("Build() error = %v", err)
}
if err := Execute(context.Background(), req, plan); err != nil {
t.Fatalf("Execute() error = %v", err)
}
destinationState := readFakeState(t, destinationBackend, "")
outputs := outputsByPath(destinationState.Outputs)
for _, path := range tt.wantPaths {
if _, ok := outputs[path]; !ok {
t.Fatalf("state outputs = %#v, missing %s", destinationState.Outputs, path)
}
}
})
}
}
}
type failingBackend struct {
*fake.Backend
failPath string
}
func (b *failingBackend) WriteFile(ctx context.Context, path string, data []byte, opts storage.WriteOptions) (storage.Entry, error) {
if path == b.failPath {
return storage.Entry{}, fmt.Errorf("injected write failure")
}
return b.Backend.WriteFile(ctx, path, data, opts)
}
func (b *failingBackend) WriteFrom(ctx context.Context, path string, r io.Reader, opts storage.WriteOptions) (storage.Entry, error) {
if path == b.failPath {
return storage.Entry{}, fmt.Errorf("injected write failure")
}
return b.Backend.WriteFrom(ctx, path, r, opts)
}
func testRequest(sourceBackend storage.Backend, destinationBackend storage.Backend, sourceBundle bundle.Bundle, reconciliationMode string) Request {
return Request{
PipelineID: "reports",
DestinationID: "archive",
SourceBundle: sourceBundle,
SourceBackend: sourceBackend,
DestinationBackend: destinationBackend,
DestinationBundlePath: sourceBundle.RootRelativePath,
Publish: config.PublishPolicy{Source: true},
Reconciliation: config.ReconciliationPolicy{Mode: reconciliationMode},
Transfer: config.TransferPolicy{
OnDestinationSame: config.TransferActionSkip,
OnDestinationOlder: config.TransferActionReplace,
OnDestinationNewer: config.TransferActionSkip,
OnConflict: config.TransferActionFail,
},
DistributorVersion: "test",
}
}
func readFakeState(t *testing.T, backend storage.Backend, bundlePath string) state.DistributorState {
func readCatalogState(t *testing.T, backend *fake.Backend, relative string) state.CatalogState {
t.Helper()
statePath, err := storage.StatePath(bundlePath)
statePath, err := storage.StatePath(relative)
if err != nil {
t.Fatalf("state path: %v", err)
}
data, err := backend.ReadFile(context.Background(), statePath)
if err != nil {
t.Fatalf("read state: %v", err)
t.Fatalf("read catalog state: %v", err)
}
destinationState, err := state.Parse(data)
catalog, err := state.ParseCatalog(data)
if err != nil {
t.Fatalf("parse state: %v", err)
t.Fatalf("parse catalog state: %v", err)
}
return destinationState
}
func outputsByPath(outputs []state.OutputFile) map[string]state.OutputFile {
byPath := make(map[string]state.OutputFile, len(outputs))
for _, output := range outputs {
byPath[output.Path] = output
}
return byPath
return catalog
}

View File

@@ -1,193 +0,0 @@
package publish
import (
"context"
"strings"
"testing"
"gitea.maximumdirect.net/eric/distributor/internal/bundle"
"gitea.maximumdirect.net/eric/distributor/internal/config"
"gitea.maximumdirect.net/eric/distributor/internal/storage/fake"
"gitea.maximumdirect.net/eric/distributor/internal/testutil"
)
func TestBuildPlansForcedReplacementOnlyWhenExplicit(t *testing.T) {
tests := []struct {
name string
prepare func(t *testing.T, backend *fake.Backend, source bundle.Manifest)
transfer config.TransferPolicy
wantReason string
forceAction bool
}{
{
name: "unmanaged content",
prepare: func(t *testing.T, backend *fake.Backend, source bundle.Manifest) {
t.Helper()
testutil.WriteFakeFile(t, backend, "bundle/old.txt", "old")
},
transfer: defaultTransfer(),
wantReason: "fail_unmanaged",
forceAction: true,
},
{
name: "different source id",
prepare: func(t *testing.T, backend *fake.Backend, source bundle.Manifest) {
t.Helper()
conflict := source
conflict.ID = "other.source"
testutil.WriteFakeDestinationState(t, backend, "bundle", conflict, testutil.DestinationStateOptions{})
},
transfer: conflictReplaceTransfer(),
wantReason: "requires --force",
forceAction: true,
},
{
name: "same created digest conflict",
prepare: func(t *testing.T, backend *fake.Backend, source bundle.Manifest) {
t.Helper()
conflict := testutil.ValidManifest(testutil.BundleOptions{Files: []testutil.SourceFile{{Path: "report.md", Data: "# Different\n"}}})
testutil.WriteFakeDestinationState(t, backend, "bundle", conflict, testutil.DestinationStateOptions{})
},
transfer: conflictReplaceTransfer(),
wantReason: "requires --force",
forceAction: true,
},
{
name: "pipeline mismatch",
prepare: func(t *testing.T, backend *fake.Backend, source bundle.Manifest) {
t.Helper()
testutil.WriteFakeDestinationState(t, backend, "bundle", source, testutil.DestinationStateOptions{PipelineID: "other-pipeline"})
},
transfer: conflictReplaceTransfer(),
wantReason: "requires --force",
forceAction: true,
},
{
name: "destination mismatch",
prepare: func(t *testing.T, backend *fake.Backend, source bundle.Manifest) {
t.Helper()
testutil.WriteFakeDestinationState(t, backend, "bundle", source, testutil.DestinationStateOptions{DestinationID: "other-destination"})
},
transfer: conflictReplaceTransfer(),
wantReason: "requires --force",
forceAction: true,
},
{
name: "newer destination",
prepare: func(t *testing.T, backend *fake.Backend, source bundle.Manifest) {
t.Helper()
newer := source
newer.Created = newer.Created.AddDate(0, 0, 1)
testutil.WriteFakeDestinationState(t, backend, "bundle", newer, testutil.DestinationStateOptions{})
},
transfer: newerReplaceTransfer(),
wantReason: "requires --force",
forceAction: true,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
sourceBackend := fake.New()
sourceBundle := testutil.WriteFakeSourceBundle(t, sourceBackend, "bundle", testutil.BundleOptions{})
destinationBackend := fake.New()
tt.prepare(t, destinationBackend, sourceBundle.Manifest)
req := forceRequest(sourceBackend, destinationBackend, sourceBundle, tt.transfer)
_, err := Build(context.Background(), req)
if err == nil || !strings.Contains(err.Error(), tt.wantReason) {
t.Fatalf("Build() error = %v, want %q", err, tt.wantReason)
}
req.Force = true
plan, err := Build(context.Background(), req)
if tt.forceAction {
if err != nil {
t.Fatalf("Build() with force error = %v", err)
}
if plan.Action != ActionForceReplace || !plan.Force {
t.Fatalf("forced plan action = %s force=%t", plan.Action, plan.Force)
}
}
})
}
}
func TestBuildRequiresConflictPolicyForStateConflicts(t *testing.T) {
sourceBackend := fake.New()
sourceBundle := testutil.WriteFakeSourceBundle(t, sourceBackend, "bundle", testutil.BundleOptions{})
destinationBackend := fake.New()
conflict := sourceBundle.Manifest
conflict.ID = "other.source"
testutil.WriteFakeDestinationState(t, destinationBackend, "bundle", conflict, testutil.DestinationStateOptions{})
req := forceRequest(sourceBackend, destinationBackend, sourceBundle, defaultTransfer())
req.Force = true
_, err := Build(context.Background(), req)
if err == nil || !strings.Contains(err.Error(), "destination source id differs") {
t.Fatalf("Build() error = %v, want conservative conflict", err)
}
}
func TestExecuteForcedReplacementDeletesOnlyBundlePath(t *testing.T) {
sourceBackend := fake.New()
sourceBundle := testutil.WriteFakeSourceBundle(t, sourceBackend, "bundle", testutil.BundleOptions{})
destinationBackend := fake.New()
testutil.WriteFakeFile(t, destinationBackend, "bundle/old.txt", "old")
testutil.WriteFakeFile(t, destinationBackend, "bundle/nested/old.txt", "old")
testutil.WriteFakeFile(t, destinationBackend, "bundle-sibling/keep.txt", "keep")
testutil.WriteFakeFile(t, destinationBackend, "outside.txt", "outside")
req := forceRequest(sourceBackend, destinationBackend, sourceBundle, defaultTransfer())
req.Force = true
plan, err := Build(context.Background(), req)
if err != nil {
t.Fatalf("Build() error = %v", err)
}
if plan.Action != ActionForceReplace {
t.Fatalf("plan action = %s, want force_replace", plan.Action)
}
if err := Execute(context.Background(), req, plan); err != nil {
t.Fatalf("Execute() error = %v", err)
}
testutil.AssertFakeFile(t, destinationBackend, "bundle/report.md", "# Report\nSunny.\n")
testutil.AssertFakeMissing(t, destinationBackend, "bundle/old.txt")
testutil.AssertFakeMissing(t, destinationBackend, "bundle/nested/old.txt")
testutil.AssertFakeFile(t, destinationBackend, "bundle-sibling/keep.txt", "keep")
testutil.AssertFakeFile(t, destinationBackend, "outside.txt", "outside")
}
func forceRequest(sourceBackend, destinationBackend *fake.Backend, sourceBundle bundle.Bundle, transfer config.TransferPolicy) Request {
return Request{
PipelineID: "reports",
DestinationID: "archive",
SourceBundle: sourceBundle,
SourceBackend: sourceBackend,
DestinationBackend: destinationBackend,
DestinationBundlePath: sourceBundle.RootRelativePath,
Publish: config.PublishPolicy{Source: true},
Transfer: transfer,
DistributorVersion: "test",
}
}
func defaultTransfer() config.TransferPolicy {
return config.TransferPolicy{
OnDestinationSame: config.TransferActionSkip,
OnDestinationOlder: config.TransferActionReplace,
OnDestinationNewer: config.TransferActionSkip,
OnConflict: config.TransferActionFail,
}
}
func conflictReplaceTransfer() config.TransferPolicy {
transfer := defaultTransfer()
transfer.OnConflict = config.TransferActionReplace
return transfer
}
func newerReplaceTransfer() config.TransferPolicy {
transfer := defaultTransfer()
transfer.OnDestinationNewer = config.TransferActionReplace
return transfer
}

View File

@@ -29,6 +29,7 @@ func PlanOutputs(ctx context.Context, req Request) ([]Output, error) {
Markdown: transform.MarkdownOptions{
Mode: req.Transform.MarkdownToHTML.Mode,
Input: req.Transform.MarkdownToHTML.Input,
CssHref: req.Transform.MarkdownToHTML.CssHref,
},
})
if err != nil {

View File

@@ -167,6 +167,7 @@ func TestPlanOutputsPassesMarkdownOptions(t *testing.T) {
Enabled: true,
Mode: config.TransformModeIndex,
Input: "report.md",
CssHref: "/assets/report.css",
}},
Transformers: testResolver{transform.MarkdownToHTML: transformer},
})
@@ -174,8 +175,8 @@ func TestPlanOutputsPassesMarkdownOptions(t *testing.T) {
if err != nil {
t.Fatalf("PlanOutputs() error = %v", err)
}
if transformer.request.Markdown.Mode != config.TransformModeIndex || transformer.request.Markdown.Input != "report.md" {
t.Fatalf("markdown options = %#v, want index/report.md", transformer.request.Markdown)
if transformer.request.Markdown.Mode != config.TransformModeIndex || transformer.request.Markdown.Input != "report.md" || transformer.request.Markdown.CssHref != "/assets/report.css" {
t.Fatalf("markdown options = %#v, want index/report.md with css href", transformer.request.Markdown)
}
}
@@ -193,12 +194,6 @@ func TestBuildRejectsHTMLWithoutTransform(t *testing.T) {
DestinationBundlePath: "",
SourceBundle: sourceBundle,
Publish: config.PublishPolicy{HTML: true},
Transfer: config.TransferPolicy{
OnDestinationSame: config.TransferActionSkip,
OnDestinationOlder: config.TransferActionReplace,
OnDestinationNewer: config.TransferActionSkip,
OnConflict: config.TransferActionFail,
},
})
if err == nil {
t.Fatal("Build() error = nil, want missing transform error")

View File

@@ -3,6 +3,7 @@ package publish
import (
"context"
"fmt"
"time"
"gitea.maximumdirect.net/eric/distributor/internal/bundle"
"gitea.maximumdirect.net/eric/distributor/internal/config"
@@ -16,11 +17,16 @@ type Action string
const (
ActionPublishNew Action = "publish_new"
ActionReplaceOlder Action = "replace_older"
ActionReplaceConflict Action = "replace_conflict"
ActionReplaceNewer Action = "replace_newer"
ActionSkipSame Action = "skip_same"
ActionSkipDestinationNewer Action = "skip_destination_newer"
ActionFailConflict Action = "fail_conflict"
ActionFailUnmanaged Action = "fail_unmanaged"
ActionForceReplace Action = "force_replace"
ActionReplaceTakeover Action = "replace_takeover"
ActionUpsertAdditive Action = "upsert_additive"
ActionReplaceCatalog Action = "replace_catalog"
)
type Request struct {
@@ -34,18 +40,28 @@ type Request struct {
Publish config.PublishPolicy
Transform config.Transform
Links *config.Links
State config.StatePolicy
Reconciliation config.ReconciliationPolicy
Workflow string
Transformers TransformerResolver
Transfer config.TransferPolicy
DistributorVersion string
Force bool
Now time.Time
}
type TransformerResolver interface {
Get(name string) (transform.Transformer, bool)
}
type Output struct {
SourcePath string
DestinationPath string
Kind string
Transform string
URL string
Data []byte
SHA256 string
Size int64
}
type Plan struct {
PipelineID string
DestinationID string
@@ -57,27 +73,36 @@ type Plan struct {
Reason string
Force bool
PrimaryURL string
StateMode string
Workflow string
OwnerScope state.OwnerScope
Reconciliation config.ReconciliationPolicy
Outputs []Output
ExistingCatalog *state.CatalogState
SupersededLegacy *state.SupersededLegacyState
CatalogOutputsToWrite []state.CatalogOutputFile
CatalogOutputsToRetain []state.CatalogOutputFile
CatalogOutputsToDelete []state.CatalogOutputFile
ClearDestinationRoot bool
// Retained while the executor is migrated to catalog state.
StateMode string
Reconciliation config.ReconciliationPolicy
TakeoverMode string
ExistingState *state.DistributorState
ExistingSharedRoot *state.SharedRootState
OtherOwnerOutputs []state.SharedRootOutputFile
TakenOverOwnerOutputs []state.SharedRootOutputFile
RetainedOwnerOutputs []state.SharedRootOutputFile
OwnerOutputsToDelete []state.SharedRootOutputFile
OwnerOutputsToWrite []Output
}
type Output struct {
SourcePath string
DestinationPath string
Kind string
Transform string
URL string
Data []byte
SHA256 string
Size int64
type catalogPlanDetails struct {
Action Action
Reason string
CatalogOutputsToWrite []state.CatalogOutputFile
CatalogOutputsToRetain []state.CatalogOutputFile
CatalogOutputsToDelete []state.CatalogOutputFile
ClearDestinationRoot bool
}
func Build(ctx context.Context, req Request) (Plan, error) {
@@ -96,10 +121,9 @@ func Build(ctx context.Context, req Request) (Plan, error) {
if err != nil {
return Plan{}, err
}
comparison := compareDestination(req, status)
action, reason := actionForComparison(comparison, req.Transfer, req.Force)
reconciliation := normalizeReconciliation(req.Reconciliation)
stateMode := normalizeState(req.State).Mode
workflow := normalizeWorkflow(req.Workflow)
scope := state.CurrentOwnerScope(req.PipelineID, req.DestinationID)
now := requestTime(req)
plan := Plan{
PipelineID: req.PipelineID,
DestinationID: req.DestinationID,
@@ -107,32 +131,37 @@ func Build(ctx context.Context, req Request) (Plan, error) {
BundlePath: req.SourceBundle.RootRelativePath,
DestinationBundlePath: req.DestinationBundlePath,
PathMapping: req.PathMapping,
Action: action,
Reason: reason,
Force: action == ActionForceReplace,
PrimaryURL: primaryURL,
StateMode: stateMode,
OwnerScope: state.CurrentOwnerScope(req.PipelineID, req.DestinationID),
Reconciliation: reconciliation,
Workflow: workflow,
OwnerScope: scope,
Outputs: outputs,
ExistingState: status.State,
ExistingSharedRoot: status.SharedRoot,
ExistingCatalog: status.Catalog,
SupersededLegacy: status.SupersededLegacy,
}
if stateMode == config.StateModeSharedRoot {
sharedDetails, err := planSharedRootOwner(ctx, req, status, action, reconciliation, outputs)
plan.OtherOwnerOutputs = sharedDetails.OtherOwnerOutputs
plan.RetainedOwnerOutputs = sharedDetails.RetainedOwnerOutputs
plan.OwnerOutputsToDelete = sharedDetails.OwnerOutputsToDelete
plan.OwnerOutputsToWrite = sharedDetails.OwnerOutputsToWrite
if status.StateErr != nil {
plan.Action = ActionFailConflict
plan.Reason = status.StateErr.Error()
return plan, fmt.Errorf("%s: %s", plan.Action, plan.Reason)
}
var details catalogPlanDetails
switch {
case status.Catalog != nil:
details, err = planExistingCatalog(ctx, req, *status.Catalog, outputs, workflow, scope, now)
case status.SupersededLegacy != nil:
details = planSupersededLegacy(req, outputs, workflow, scope, now)
default:
details, err = planWithoutCatalog(ctx, req, outputs, workflow, scope, now)
}
plan.Action = details.Action
plan.Reason = details.Reason
plan.CatalogOutputsToWrite = details.CatalogOutputsToWrite
plan.CatalogOutputsToRetain = details.CatalogOutputsToRetain
plan.CatalogOutputsToDelete = details.CatalogOutputsToDelete
plan.ClearDestinationRoot = details.ClearDestinationRoot
if err != nil {
plan.Action = sharedDetails.Action
plan.Reason = sharedDetails.Reason
return plan, err
}
}
if action == ActionFailConflict || action == ActionFailUnmanaged {
return plan, fmt.Errorf("%s: %s", action, reason)
}
return plan, nil
}
@@ -152,139 +181,134 @@ func validateRequest(req Request) error {
if err := config.ValidatePublishTransformPolicy(req.Publish, req.Transform); err != nil {
return fmt.Errorf("publish/transform policy: %w", err)
}
switch normalizeReconciliation(req.Reconciliation).Mode {
case config.ReconciliationModeReplace, config.ReconciliationModeMerge:
switch normalizeWorkflow(req.Workflow) {
case config.WorkflowAdditive, config.WorkflowReplacement:
default:
return fmt.Errorf("reconciliation.mode must be %s or %s", config.ReconciliationModeReplace, config.ReconciliationModeMerge)
}
switch normalizeState(req.State).Mode {
case config.StateModeSingleOwner, config.StateModeSharedRoot:
default:
return fmt.Errorf("state.mode must be %s or %s", config.StateModeSingleOwner, config.StateModeSharedRoot)
return fmt.Errorf("destination.workflow must be %s or %s", config.WorkflowAdditive, config.WorkflowReplacement)
}
return nil
}
func normalizeReconciliation(policy config.ReconciliationPolicy) config.ReconciliationPolicy {
if policy.Mode == "" {
policy.Mode = config.ReconciliationModeReplace
func normalizeWorkflow(workflow string) string {
if workflow == "" {
return config.WorkflowAdditive
}
return policy
return workflow
}
func normalizeState(policy config.StatePolicy) config.StatePolicy {
if policy.Mode == "" {
policy.Mode = config.StateModeSingleOwner
func requestTime(req Request) time.Time {
if req.Now.IsZero() {
return time.Now().UTC()
}
return policy
return req.Now.UTC()
}
func compareDestination(req Request, status state.DestinationStatus) state.Comparison {
if normalizeState(req.State).Mode == config.StateModeSharedRoot {
scope := state.CurrentOwnerScope(req.PipelineID, req.DestinationID)
comparison := state.CompareSharedRootOwner(req.SourceBundle.Manifest, scope, status)
if req.PathMapping != config.PathMappingFixed || comparison.Outcome != state.OutcomeDifferentSourceConflict {
return comparison
func planExistingCatalog(ctx context.Context, req Request, catalog state.CatalogState, outputs []Output, workflow string, scope state.OwnerScope, now time.Time) (catalogPlanDetails, error) {
if err := rejectCatalogUnmanagedCollisions(ctx, req.DestinationBackend, req.DestinationBundlePath, catalog.Outputs, outputs); err != nil {
return catalogPlanDetails{
Action: ActionFailUnmanaged,
Reason: err.Error(),
}, fmt.Errorf("%s: %s", ActionFailUnmanaged, err)
}
destinationManifest, ok := sharedRootComparisonManifest(status, scope)
if !ok {
return comparison
planned := outputPathSet(outputs)
details := catalogPlanDetails{
Action: actionForWorkflow(workflow),
CatalogOutputsToWrite: catalogOutputsForPlan(req, outputs, catalog.Outputs, scope, now),
}
if destinationManifest.Created.Before(req.SourceBundle.Manifest.Created) {
return state.Comparison{Outcome: state.OutcomeDestinationOlder, Reason: "fixed destination source is older than selected source"}
}
if destinationManifest.Created.After(req.SourceBundle.Manifest.Created) {
return state.Comparison{Outcome: state.OutcomeDestinationNewer, Reason: "fixed destination source is newer than selected source"}
}
return comparison
}
comparison := state.Compare(req.SourceBundle.Manifest, req.PipelineID, req.DestinationID, status)
if req.PathMapping != config.PathMappingFixed || comparison.Outcome != state.OutcomeDifferentSourceConflict || status.State == nil {
return comparison
}
destinationManifest := status.State.Source.Manifest
if destinationManifest.Created.Before(req.SourceBundle.Manifest.Created) {
return state.Comparison{Outcome: state.OutcomeDestinationOlder, Reason: "fixed destination source is older than selected source"}
}
if destinationManifest.Created.After(req.SourceBundle.Manifest.Created) {
return state.Comparison{Outcome: state.OutcomeDestinationNewer, Reason: "fixed destination source is newer than selected source"}
}
return comparison
}
func sharedRootComparisonManifest(status state.DestinationStatus, scope state.OwnerScope) (bundle.Manifest, bool) {
if status.SharedRoot != nil {
return status.SharedRoot.SourceManifest(scope)
}
if status.State != nil && status.State.PipelineID == scope.PipelineID && status.State.DestinationID == scope.DestinationID {
return status.State.Source.Manifest, true
}
return bundle.Manifest{}, false
}
type sharedRootPlanDetails struct {
Action Action
Reason string
OtherOwnerOutputs []state.SharedRootOutputFile
RetainedOwnerOutputs []state.SharedRootOutputFile
OwnerOutputsToDelete []state.SharedRootOutputFile
OwnerOutputsToWrite []Output
}
func planSharedRootOwner(ctx context.Context, req Request, status state.DestinationStatus, action Action, reconciliation config.ReconciliationPolicy, outputs []Output) (sharedRootPlanDetails, error) {
scope := state.CurrentOwnerScope(req.PipelineID, req.DestinationID)
details := sharedRootPlanDetails{Action: action}
if !isWriteAction(action) {
details.OtherOwnerOutputs = otherOwnerOutputs(status, scope)
return details, nil
}
plannedPaths := outputPaths(outputs)
if action == ActionForceReplace {
details.OwnerOutputsToWrite = append([]Output(nil), outputs...)
return details, nil
}
if conflict, ok := sharedRootPathOwnershipConflict(status, scope, plannedPaths); ok {
reason := fmt.Sprintf("destination output path %s is owned by %s/%s", conflict.Path, conflict.Owner.PipelineID, conflict.Owner.DestinationID)
details.Action = ActionFailConflict
details.Reason = reason
return details, fmt.Errorf("%s: %s", ActionFailConflict, reason)
}
if err := rejectSharedRootUnmanagedCollisions(ctx, req.DestinationBackend, req.DestinationBundlePath, status, scope, plannedPaths); err != nil {
details.Action = ActionFailUnmanaged
details.Reason = err.Error()
return details, fmt.Errorf("%s: %s", ActionFailUnmanaged, err)
}
details.OtherOwnerOutputs = otherOwnerOutputs(status, scope)
ownerOutputs := currentOwnerOutputs(status, scope)
planned := make(map[string]struct{}, len(plannedPaths))
for _, path := range plannedPaths {
planned[path] = struct{}{}
}
for _, output := range ownerOutputs {
for _, output := range catalog.Outputs {
if _, exists := planned[output.Path]; exists {
continue
}
if action == ActionReplaceOlder && reconciliation.Mode == config.ReconciliationModeReplace {
details.OwnerOutputsToDelete = append(details.OwnerOutputsToDelete, output)
if workflow == config.WorkflowReplacement && output.PipelineID == scope.PipelineID && output.DestinationID == scope.DestinationID {
details.CatalogOutputsToDelete = append(details.CatalogOutputsToDelete, output)
continue
}
if action == ActionReplaceOlder && reconciliation.Mode == config.ReconciliationModeMerge {
details.RetainedOwnerOutputs = append(details.RetainedOwnerOutputs, output)
details.CatalogOutputsToRetain = append(details.CatalogOutputsToRetain, output)
}
}
details.OwnerOutputsToWrite = append([]Output(nil), outputs...)
return details, nil
}
func isWriteAction(action Action) bool {
switch action {
case ActionPublishNew, ActionReplaceOlder, ActionForceReplace:
return true
default:
return false
func planSupersededLegacy(req Request, outputs []Output, workflow string, scope state.OwnerScope, now time.Time) catalogPlanDetails {
details := catalogPlanDetails{
Action: actionForWorkflow(workflow),
CatalogOutputsToWrite: catalogOutputsForPlan(req, outputs, nil, scope, now),
}
if workflow == config.WorkflowReplacement {
details.ClearDestinationRoot = true
}
return details
}
func planWithoutCatalog(ctx context.Context, req Request, outputs []Output, workflow string, scope state.OwnerScope, now time.Time) (catalogPlanDetails, error) {
if err := rejectCatalogUnmanagedCollisions(ctx, req.DestinationBackend, req.DestinationBundlePath, nil, outputs); err != nil {
return catalogPlanDetails{
Action: ActionFailUnmanaged,
Reason: err.Error(),
}, fmt.Errorf("%s: %s", ActionFailUnmanaged, err)
}
return catalogPlanDetails{
Action: ActionPublishNew,
CatalogOutputsToWrite: catalogOutputsForPlan(req, outputs, nil, scope, now),
}, nil
}
func actionForWorkflow(workflow string) Action {
if workflow == config.WorkflowReplacement {
return ActionReplaceCatalog
}
return ActionUpsertAdditive
}
func catalogOutputsForPlan(req Request, outputs []Output, existing []state.CatalogOutputFile, scope state.OwnerScope, now time.Time) []state.CatalogOutputFile {
files := make([]state.CatalogOutputFile, 0, len(outputs))
source := state.CatalogSourceIdentity{
ID: req.SourceBundle.Manifest.ID,
Digest: req.SourceBundle.Manifest.Digest,
Created: req.SourceBundle.Manifest.Created,
}
for _, output := range outputs {
createdAt := now
if existingOutput, ok := state.FindCatalogOutputByPath(existing, output.DestinationPath); ok {
createdAt = existingOutput.CreatedAt
}
file := state.CatalogOutputFile{
Path: output.DestinationPath,
PipelineID: scope.PipelineID,
DestinationID: scope.DestinationID,
Source: source,
Kind: output.Kind,
URL: output.URL,
SHA256: output.SHA256,
Size: output.Size,
CreatedAt: createdAt,
UpdatedAt: now,
}
if output.Kind == state.OutputKindGenerated {
file.SourcePath = output.SourcePath
file.Transform = output.Transform
}
files = append(files, file)
}
return files
}
func rejectCatalogUnmanagedCollisions(ctx context.Context, backend storage.Backend, bundlePath string, existing []state.CatalogOutputFile, outputs []Output) error {
managed := catalogOutputPathSet(existing)
for _, output := range outputs {
if _, exists := managed[output.DestinationPath]; exists {
continue
}
destinationPath, err := storage.Join(bundlePath, output.DestinationPath)
if err != nil {
return err
}
if _, err := backend.Stat(ctx, destinationPath); err == nil {
return fmt.Errorf("destination output path %s exists but is not managed by catalog state", storage.DisplayPath(output.DestinationPath))
} else if !storage.IsNotFound(err) {
return err
}
}
return nil
}
func outputPaths(outputs []Output) []string {
@@ -295,131 +319,37 @@ func outputPaths(outputs []Output) []string {
return paths
}
func sharedRootPathOwnershipConflict(status state.DestinationStatus, scope state.OwnerScope, paths []string) (state.PathOwnershipConflict, bool) {
if status.SharedRoot != nil {
return status.SharedRoot.PathOwnershipConflict(scope, paths)
func outputPathSet(outputs []Output) map[string]struct{} {
paths := make(map[string]struct{}, len(outputs))
for _, output := range outputs {
paths[output.DestinationPath] = struct{}{}
}
return state.PathOwnershipConflict{}, false
return paths
}
func rejectSharedRootUnmanagedCollisions(ctx context.Context, backend storage.Backend, bundlePath string, status state.DestinationStatus, scope state.OwnerScope, paths []string) error {
for _, path := range paths {
if pathManagedBySharedRootStatus(status, scope, path) {
continue
func catalogOutputPathSet(outputs []state.CatalogOutputFile) map[string]struct{} {
paths := make(map[string]struct{}, len(outputs))
for _, output := range outputs {
paths[output.Path] = struct{}{}
}
destinationPath, err := storage.Join(bundlePath, path)
if err != nil {
return err
}
if _, err := backend.Stat(ctx, destinationPath); err == nil {
return fmt.Errorf("destination output path %s exists but is not managed by destination state", storage.DisplayPath(path))
} else if !storage.IsNotFound(err) {
return err
}
}
return nil
return paths
}
func pathManagedBySharedRootStatus(status state.DestinationStatus, scope state.OwnerScope, path string) bool {
if status.SharedRoot != nil {
_, exists := status.SharedRoot.OutputOwner(path)
return exists
func normalizeReconciliation(policy config.ReconciliationPolicy) config.ReconciliationPolicy {
if policy.Mode == "" {
policy.Mode = config.ReconciliationModeReplace
}
if status.State != nil && status.State.PipelineID == scope.PipelineID && status.State.DestinationID == scope.DestinationID {
_, exists := state.FindOutputByPath(status.State.Outputs, path)
return exists
}
return false
return policy
}
func otherOwnerOutputs(status state.DestinationStatus, scope state.OwnerScope) []state.SharedRootOutputFile {
if status.SharedRoot == nil {
return nil
}
outputs := make([]state.SharedRootOutputFile, 0, len(status.SharedRoot.Outputs))
for _, output := range status.SharedRoot.Outputs {
if output.Owner != scope {
outputs = append(outputs, output)
}
}
return outputs
func isReconciliationReplacementAction(action Action) bool {
return action == ActionReplaceOlder || action == ActionReplaceNewer
}
func currentOwnerOutputs(status state.DestinationStatus, scope state.OwnerScope) []state.SharedRootOutputFile {
if status.SharedRoot != nil {
outputs := make([]state.SharedRootOutputFile, 0, len(status.SharedRoot.Outputs))
for _, output := range status.SharedRoot.Outputs {
if output.Owner == scope {
outputs = append(outputs, output)
}
}
return outputs
}
if status.State != nil && status.State.PipelineID == scope.PipelineID && status.State.DestinationID == scope.DestinationID {
outputs := make([]state.SharedRootOutputFile, 0, len(status.State.Outputs))
for _, output := range status.State.Outputs {
outputs = append(outputs, state.SharedRootOutputFile{
Path: output.Path,
Kind: output.Kind,
SourcePath: output.SourcePath,
Transform: output.Transform,
URL: output.URL,
SHA256: output.SHA256,
Size: output.Size,
Owner: scope,
SourceID: status.State.Source.Manifest.ID,
SourceDigest: status.State.Source.Manifest.Digest,
SourceCreated: status.State.Source.Manifest.Created,
CreatedAt: output.CreatedAt,
UpdatedAt: output.UpdatedAt,
})
}
return outputs
}
return nil
}
func actionForComparison(comparison state.Comparison, transfer config.TransferPolicy, force bool) (Action, string) {
switch comparison.Outcome {
case state.OutcomeDestinationAbsent:
return ActionPublishNew, comparison.Reason
case state.OutcomeDestinationUnmanaged:
if force {
return ActionForceReplace, "forced replacement of unmanaged destination content"
}
return ActionFailUnmanaged, comparison.Reason
case state.OutcomeInvalidState:
return ActionFailConflict, comparison.Reason
case state.OutcomeIdentityMismatch, state.OutcomeSameCreatedConflict, state.OutcomeDifferentSourceConflict:
if transfer.OnConflict == config.TransferActionReplace {
if force {
return ActionForceReplace, "forced replacement of conflicting destination state: " + comparison.Reason
}
return ActionFailConflict, "destination conflict replacement requires --force"
}
return ActionFailConflict, comparison.Reason
case state.OutcomeSameSource:
if transfer.OnDestinationSame == config.TransferActionFail {
return ActionFailConflict, "destination matches source and transfer policy requires failure"
}
return ActionSkipSame, comparison.Reason
case state.OutcomeDestinationOlder:
if transfer.OnDestinationOlder == config.TransferActionFail {
return ActionFailConflict, "destination is older and transfer policy requires failure"
}
return ActionReplaceOlder, comparison.Reason
case state.OutcomeDestinationNewer:
if transfer.OnDestinationNewer == config.TransferActionReplace {
if force {
return ActionForceReplace, "forced replacement of newer destination state"
}
return ActionFailConflict, "destination is newer and replacement requires --force"
}
if transfer.OnDestinationNewer == config.TransferActionFail {
return ActionFailConflict, "destination is newer and transfer policy requires failure"
}
return ActionSkipDestinationNewer, comparison.Reason
default:
return ActionFailConflict, "unsupported comparison outcome"
func sharedRootOutputPathSet(outputs []state.SharedRootOutputFile) map[string]struct{} {
paths := make(map[string]struct{}, len(outputs))
for _, output := range outputs {
paths[output.Path] = struct{}{}
}
return paths
}

View File

@@ -0,0 +1,296 @@
package publish
import (
"context"
"encoding/json"
"strings"
"testing"
"time"
"gitea.maximumdirect.net/eric/distributor/internal/config"
"gitea.maximumdirect.net/eric/distributor/internal/state"
"gitea.maximumdirect.net/eric/distributor/internal/storage"
"gitea.maximumdirect.net/eric/distributor/internal/storage/fake"
"gitea.maximumdirect.net/eric/distributor/internal/testutil"
)
var (
planCreatedAt = time.Date(2026, 5, 30, 11, 12, 0, 0, time.UTC)
planUpdatedAt = time.Date(2026, 6, 1, 9, 30, 0, 0, time.UTC)
)
func TestBuildAdditivePublishesCatalogOutputs(t *testing.T) {
_, destinationBackend, req := catalogPlanRequest(t, config.WorkflowAdditive)
plan, err := Build(context.Background(), req)
if err != nil {
t.Fatalf("Build() error = %v", err)
}
if plan.Action != ActionPublishNew || plan.Workflow != config.WorkflowAdditive {
t.Fatalf("plan action=%s workflow=%s, want publish_new additive", plan.Action, plan.Workflow)
}
if len(plan.CatalogOutputsToWrite) != 2 || len(plan.CatalogOutputsToRetain) != 0 || len(plan.CatalogOutputsToDelete) != 0 {
t.Fatalf("catalog write=%d retain=%d delete=%d", len(plan.CatalogOutputsToWrite), len(plan.CatalogOutputsToRetain), len(plan.CatalogOutputsToDelete))
}
for _, output := range plan.CatalogOutputsToWrite {
if output.PipelineID != "reports" || output.DestinationID != "archive" {
t.Fatalf("catalog output owner = %s/%s", output.PipelineID, output.DestinationID)
}
if output.Source.ID != req.SourceBundle.Manifest.ID || output.Source.Digest != req.SourceBundle.Manifest.Digest || !output.Source.Created.Equal(req.SourceBundle.Manifest.Created) {
t.Fatalf("catalog output source = %#v", output.Source)
}
if output.Kind == state.OutputKindSource && output.SourcePath != "" {
t.Fatalf("source catalog output source_path = %q, want empty", output.SourcePath)
}
if !output.CreatedAt.Equal(planUpdatedAt) || !output.UpdatedAt.Equal(planUpdatedAt) {
t.Fatalf("catalog output times = %s/%s", output.CreatedAt, output.UpdatedAt)
}
}
if _, err := destinationBackend.Stat(context.Background(), storage.StateFileName); !storage.IsNotFound(err) {
t.Fatalf("destination state stat error = %v, want missing", err)
}
}
func TestBuildAdditiveOverwritesManagedAndRetainsOthers(t *testing.T) {
_, destinationBackend, req := catalogPlanRequest(t, config.WorkflowAdditive)
existing := baseCatalog(req)
existing.Outputs = []state.CatalogOutputFile{
catalogOutput(req, "reports", "archive", "report.md", state.OutputKindSource, planCreatedAt),
catalogOutput(req, "reports", "web", "old.txt", state.OutputKindSource, planCreatedAt),
}
writeCatalogState(t, destinationBackend, "", existing)
testutil.WriteFakeFile(t, destinationBackend, "report.md", "old")
plan, err := Build(context.Background(), req)
if err != nil {
t.Fatalf("Build() error = %v", err)
}
if plan.Action != ActionUpsertAdditive {
t.Fatalf("plan action = %s, want %s", plan.Action, ActionUpsertAdditive)
}
if len(plan.CatalogOutputsToDelete) != 0 {
t.Fatalf("delete outputs = %#v, want none", plan.CatalogOutputsToDelete)
}
if len(plan.CatalogOutputsToRetain) != 1 || plan.CatalogOutputsToRetain[0].Path != "old.txt" {
t.Fatalf("retained outputs = %#v, want old.txt", plan.CatalogOutputsToRetain)
}
written, ok := state.FindCatalogOutputByPath(plan.CatalogOutputsToWrite, "report.md")
if !ok {
t.Fatalf("written outputs = %#v, want report.md", plan.CatalogOutputsToWrite)
}
if !written.CreatedAt.Equal(planCreatedAt) || !written.UpdatedAt.Equal(planUpdatedAt) {
t.Fatalf("report.md times = %s/%s, want created preserved and updated now", written.CreatedAt, written.UpdatedAt)
}
}
func TestBuildReplacementDeletesCurrentOwnerAndRetainsOtherOwners(t *testing.T) {
_, destinationBackend, req := catalogPlanRequest(t, config.WorkflowReplacement)
existing := baseCatalog(req)
existing.Outputs = []state.CatalogOutputFile{
catalogOutput(req, "reports", "archive", "report.md", state.OutputKindSource, planCreatedAt),
catalogOutput(req, "reports", "archive", "stale.txt", state.OutputKindSource, planCreatedAt),
catalogOutput(req, "reports", "web", "shared.txt", state.OutputKindSource, planCreatedAt),
}
writeCatalogState(t, destinationBackend, "", existing)
plan, err := Build(context.Background(), req)
if err != nil {
t.Fatalf("Build() error = %v", err)
}
if plan.Action != ActionReplaceCatalog {
t.Fatalf("plan action = %s, want %s", plan.Action, ActionReplaceCatalog)
}
if len(plan.CatalogOutputsToDelete) != 1 || plan.CatalogOutputsToDelete[0].Path != "stale.txt" {
t.Fatalf("delete outputs = %#v, want stale.txt", plan.CatalogOutputsToDelete)
}
if len(plan.CatalogOutputsToRetain) != 1 || plan.CatalogOutputsToRetain[0].Path != "shared.txt" {
t.Fatalf("retained outputs = %#v, want shared.txt", plan.CatalogOutputsToRetain)
}
}
func TestBuildTransfersManagedPathOwnership(t *testing.T) {
_, destinationBackend, req := catalogPlanRequest(t, config.WorkflowReplacement)
existing := baseCatalog(req)
existing.Outputs = []state.CatalogOutputFile{
catalogOutput(req, "reports", "web", "report.md", state.OutputKindSource, planCreatedAt),
}
writeCatalogState(t, destinationBackend, "", existing)
plan, err := Build(context.Background(), req)
if err != nil {
t.Fatalf("Build() error = %v", err)
}
written, ok := state.FindCatalogOutputByPath(plan.CatalogOutputsToWrite, "report.md")
if !ok {
t.Fatalf("written outputs = %#v, want report.md", plan.CatalogOutputsToWrite)
}
if written.PipelineID != "reports" || written.DestinationID != "archive" {
t.Fatalf("written owner = %s/%s, want reports/archive", written.PipelineID, written.DestinationID)
}
if !written.CreatedAt.Equal(planCreatedAt) || !written.UpdatedAt.Equal(planUpdatedAt) {
t.Fatalf("written times = %s/%s", written.CreatedAt, written.UpdatedAt)
}
if len(plan.CatalogOutputsToRetain) != 0 || len(plan.CatalogOutputsToDelete) != 0 {
t.Fatalf("retain=%#v delete=%#v, want no old record for overwritten path", plan.CatalogOutputsToRetain, plan.CatalogOutputsToDelete)
}
}
func TestBuildRejectsUnmanagedPlannedPathCollision(t *testing.T) {
_, destinationBackend, req := catalogPlanRequest(t, config.WorkflowAdditive)
testutil.WriteFakeFile(t, destinationBackend, "report.md", "unmanaged")
plan, err := Build(context.Background(), req)
if err == nil {
t.Fatal("Build() error = nil, want unmanaged collision")
}
if plan.Action != ActionFailUnmanaged || !strings.Contains(err.Error(), "not managed by catalog state") {
t.Fatalf("plan action=%s error=%v, want unmanaged catalog collision", plan.Action, err)
}
}
func TestBuildPlansSupersededLegacyAdditive(t *testing.T) {
_, destinationBackend, req := catalogPlanRequest(t, config.WorkflowAdditive)
legacyState := testutil.DestinationState(req.SourceBundle.Manifest, testutil.DestinationStateOptions{})
writeJSONState(t, destinationBackend, "", legacyState)
testutil.WriteFakeFile(t, destinationBackend, "report.md", "legacy")
plan, err := Build(context.Background(), req)
if err != nil {
t.Fatalf("Build() error = %v", err)
}
if plan.SupersededLegacy == nil || plan.SupersededLegacy.SchemaVersion != state.SchemaVersion {
t.Fatalf("superseded legacy = %#v", plan.SupersededLegacy)
}
if plan.Action != ActionUpsertAdditive || plan.ClearDestinationRoot {
t.Fatalf("plan action=%s clear=%t, want additive overwrite without clear", plan.Action, plan.ClearDestinationRoot)
}
}
func TestBuildPlansSupersededLegacyReplacementClear(t *testing.T) {
_, destinationBackend, req := catalogPlanRequest(t, config.WorkflowReplacement)
legacyState := testutil.DestinationState(req.SourceBundle.Manifest, testutil.DestinationStateOptions{})
writeJSONState(t, destinationBackend, "", legacyState)
plan, err := Build(context.Background(), req)
if err != nil {
t.Fatalf("Build() error = %v", err)
}
if plan.Action != ActionReplaceCatalog || !plan.ClearDestinationRoot {
t.Fatalf("plan action=%s clear=%t, want replacement clear", plan.Action, plan.ClearDestinationRoot)
}
}
func TestBuildRejectsInvalidOrFutureState(t *testing.T) {
tests := []struct {
name string
data string
}{
{name: "invalid json", data: `{"schema_version":`},
{name: "future schema", data: `{"schema_version":99}`},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
_, destinationBackend, req := catalogPlanRequest(t, config.WorkflowAdditive)
testutil.WriteFakeFile(t, destinationBackend, storage.StateFileName, tt.data)
plan, err := Build(context.Background(), req)
if err == nil {
t.Fatal("Build() error = nil, want conflict")
}
if plan.Action != ActionFailConflict {
t.Fatalf("plan action = %s, want %s", plan.Action, ActionFailConflict)
}
})
}
}
func TestValidateRequestRejectsInvalidWorkflow(t *testing.T) {
sourceBackend, destinationBackend, req := catalogPlanRequest(t, "append")
req.SourceBackend = sourceBackend
req.DestinationBackend = destinationBackend
err := validateRequest(req)
if err == nil {
t.Fatal("validateRequest() error = nil, want invalid workflow")
}
if !strings.Contains(err.Error(), "destination.workflow") {
t.Fatalf("validateRequest() error = %v, want workflow context", err)
}
}
func catalogPlanRequest(t *testing.T, workflow string) (*fake.Backend, *fake.Backend, Request) {
t.Helper()
sourceBackend := fake.New()
destinationBackend := fake.New()
sourceBundle := testutil.WriteFakeSourceBundle(t, sourceBackend, "", testutil.BundleOptions{})
return sourceBackend, destinationBackend, Request{
PipelineID: "reports",
DestinationID: "archive",
SourceBundle: sourceBundle,
SourceBackend: sourceBackend,
DestinationBackend: destinationBackend,
DestinationBundlePath: "",
PathMapping: config.PathMappingPreserveRelative,
Publish: config.PublishPolicy{Source: true},
Workflow: workflow,
DistributorVersion: "test",
Now: planUpdatedAt,
}
}
func baseCatalog(req Request) state.CatalogState {
return state.CatalogState{
SchemaVersion: state.CatalogSchemaVersion,
DistributorVersion: "previous",
CreatedAt: planCreatedAt,
UpdatedAt: planCreatedAt,
State: state.StatePolicy{Mode: state.StateModeCatalog},
Outputs: []state.CatalogOutputFile{},
}
}
func catalogOutput(req Request, pipelineID, destinationID, path, kind string, createdAt time.Time) state.CatalogOutputFile {
sourceSHA := req.SourceBundle.Manifest.Files[0].SHA256
sourceSize := req.SourceBundle.Manifest.Files[0].Size
for _, file := range req.SourceBundle.Manifest.Files {
if file.Path == path {
sourceSHA = file.SHA256
sourceSize = file.Size
break
}
}
output := state.CatalogOutputFile{
Path: path,
PipelineID: pipelineID,
DestinationID: destinationID,
Source: state.CatalogSourceIdentity{
ID: req.SourceBundle.Manifest.ID,
Digest: req.SourceBundle.Manifest.Digest,
Created: req.SourceBundle.Manifest.Created,
},
Kind: kind,
SHA256: sourceSHA,
Size: sourceSize,
CreatedAt: createdAt,
UpdatedAt: createdAt,
}
return output
}
func writeCatalogState(t *testing.T, backend *fake.Backend, relative string, catalog state.CatalogState) {
t.Helper()
writeJSONState(t, backend, relative, catalog)
}
func writeJSONState(t *testing.T, backend *fake.Backend, relative string, value any) {
t.Helper()
data, err := json.MarshalIndent(value, "", " ")
if err != nil {
t.Fatalf("marshal state: %v", err)
}
statePath, err := storage.StatePath(relative)
if err != nil {
t.Fatalf("state path: %v", err)
}
testutil.WriteFakeFile(t, backend, statePath, string(append(data, '\n')))
}

View File

@@ -18,7 +18,13 @@ func inspectDestination(ctx context.Context, backend storage.Backend, bundlePath
if parseErr != nil {
return state.DestinationStatus{StateErr: parseErr}, nil
}
return state.DestinationStatus{State: document.SingleOwner, SharedRoot: document.SharedRoot, HasContents: true}, nil
return state.DestinationStatus{
State: document.SingleOwner,
SharedRoot: document.SharedRoot,
Catalog: document.Catalog,
SupersededLegacy: document.SupersededLegacy,
HasContents: true,
}, nil
}
if !storage.IsNotFound(err) {
return state.DestinationStatus{}, err

View File

@@ -1,399 +0,0 @@
package publish
import (
"context"
"encoding/json"
"strings"
"testing"
"time"
"gitea.maximumdirect.net/eric/distributor/internal/bundle"
"gitea.maximumdirect.net/eric/distributor/internal/config"
"gitea.maximumdirect.net/eric/distributor/internal/state"
"gitea.maximumdirect.net/eric/distributor/internal/storage"
"gitea.maximumdirect.net/eric/distributor/internal/storage/fake"
"gitea.maximumdirect.net/eric/distributor/internal/testutil"
)
func TestBuildSharedRootTreatsAbsentOwnerAsPublishable(t *testing.T) {
sourceBackend := fake.New()
sourceBundle := testutil.WriteFakeSourceBundle(t, sourceBackend, "bundle", testutil.BundleOptions{
Files: []testutil.SourceFile{{Path: "report.md", Data: "# Report\n"}},
})
destinationBackend := fake.New()
writeFakeSharedRootState(t, destinationBackend, "bundle", sharedRootStateWithOwners(t, sourceBundle.Manifest, false))
req := sharedRootRequest(sourceBackend, destinationBackend, sourceBundle, config.ReconciliationModeReplace)
plan, err := Build(context.Background(), req)
if err != nil {
t.Fatalf("Build() error = %v", err)
}
if plan.Action != ActionPublishNew {
t.Fatalf("plan action = %s, want publish_new", plan.Action)
}
if plan.OwnerScope != state.CurrentOwnerScope("reports", "archive") {
t.Fatalf("owner scope = %#v, want reports/archive", plan.OwnerScope)
}
if got, want := len(plan.OtherOwnerOutputs), 1; got != want {
t.Fatalf("other owner output count = %d, want %d", got, want)
}
if got, want := len(plan.OwnerOutputsToWrite), 1; got != want {
t.Fatalf("owner output write count = %d, want %d", got, want)
}
if len(plan.OwnerOutputsToDelete) != 0 || len(plan.RetainedOwnerOutputs) != 0 {
t.Fatalf("delete=%#v retained=%#v, want none", plan.OwnerOutputsToDelete, plan.RetainedOwnerOutputs)
}
}
func TestBuildSharedRootReplaceDeletesOnlyCurrentOwnerOmittedOutputs(t *testing.T) {
sourceBackend := fake.New()
sourceBundle := testutil.WriteFakeSourceBundle(t, sourceBackend, "bundle", testutil.BundleOptions{
Files: []testutil.SourceFile{{Path: "report.md", Data: "# Report\nNew.\n"}},
})
destinationBackend := fake.New()
writeFakeSharedRootState(t, destinationBackend, "bundle", sharedRootStateWithOwners(t, sourceBundle.Manifest, true))
req := sharedRootRequest(sourceBackend, destinationBackend, sourceBundle, config.ReconciliationModeReplace)
plan, err := Build(context.Background(), req)
if err != nil {
t.Fatalf("Build() error = %v", err)
}
if plan.Action != ActionReplaceOlder {
t.Fatalf("plan action = %s, want replace_older", plan.Action)
}
if got, want := sharedRootOutputPathList(plan.OwnerOutputsToDelete), "old.md"; got != want {
t.Fatalf("owner outputs to delete = %q, want %q", got, want)
}
if got, want := sharedRootOutputPathList(plan.OtherOwnerOutputs), "other/report.md"; got != want {
t.Fatalf("other owner outputs = %q, want %q", got, want)
}
if len(plan.RetainedOwnerOutputs) != 0 {
t.Fatalf("retained owner outputs = %#v, want none", plan.RetainedOwnerOutputs)
}
}
func TestBuildSharedRootMergeRetainsCurrentOwnerOmittedOutputs(t *testing.T) {
sourceBackend := fake.New()
sourceBundle := testutil.WriteFakeSourceBundle(t, sourceBackend, "bundle", testutil.BundleOptions{
Files: []testutil.SourceFile{{Path: "report.md", Data: "# Report\nNew.\n"}},
})
destinationBackend := fake.New()
writeFakeSharedRootState(t, destinationBackend, "bundle", sharedRootStateWithOwners(t, sourceBundle.Manifest, true))
req := sharedRootRequest(sourceBackend, destinationBackend, sourceBundle, config.ReconciliationModeMerge)
plan, err := Build(context.Background(), req)
if err != nil {
t.Fatalf("Build() error = %v", err)
}
if got, want := sharedRootOutputPathList(plan.RetainedOwnerOutputs), "old.md"; got != want {
t.Fatalf("retained owner outputs = %q, want %q", got, want)
}
if len(plan.OwnerOutputsToDelete) != 0 {
t.Fatalf("owner outputs to delete = %#v, want none", plan.OwnerOutputsToDelete)
}
}
func TestBuildSharedRootRejectsOtherOwnerPathConflict(t *testing.T) {
sourceBackend := fake.New()
sourceBundle := testutil.WriteFakeSourceBundle(t, sourceBackend, "bundle", testutil.BundleOptions{
Files: []testutil.SourceFile{{Path: "report.md", Data: "# Report\n"}},
})
destinationBackend := fake.New()
sharedRoot := sharedRootStateWithOwners(t, sourceBundle.Manifest, false)
sharedRoot.Outputs[0].Path = "report.md"
writeFakeSharedRootState(t, destinationBackend, "bundle", sharedRoot)
req := sharedRootRequest(sourceBackend, destinationBackend, sourceBundle, config.ReconciliationModeReplace)
plan, err := Build(context.Background(), req)
if err == nil || !strings.Contains(err.Error(), "fail_conflict") {
t.Fatalf("Build() error = %v, want fail_conflict", err)
}
if plan.Action != ActionFailConflict {
t.Fatalf("plan action = %s, want fail_conflict", plan.Action)
}
}
func TestBuildSharedRootRejectsUnmanagedPathCollision(t *testing.T) {
sourceBackend := fake.New()
sourceBundle := testutil.WriteFakeSourceBundle(t, sourceBackend, "bundle", testutil.BundleOptions{
Files: []testutil.SourceFile{{Path: "report.md", Data: "# Report\n"}},
})
destinationBackend := fake.New()
writeFakeSharedRootState(t, destinationBackend, "bundle", sharedRootStateWithOwners(t, sourceBundle.Manifest, false))
testutil.WriteFakeFile(t, destinationBackend, "bundle/report.md", "unmanaged")
req := sharedRootRequest(sourceBackend, destinationBackend, sourceBundle, config.ReconciliationModeReplace)
plan, err := Build(context.Background(), req)
if err == nil || !strings.Contains(err.Error(), "fail_unmanaged") {
t.Fatalf("Build() error = %v, want fail_unmanaged", err)
}
if plan.Action != ActionFailUnmanaged {
t.Fatalf("plan action = %s, want fail_unmanaged", plan.Action)
}
}
func TestExecuteSharedRootPublishesOwnerAndPreservesOtherOwners(t *testing.T) {
sourceBackend := fake.New()
sourceBundle := testutil.WriteFakeSourceBundle(t, sourceBackend, "bundle", testutil.BundleOptions{
Files: []testutil.SourceFile{{Path: "report.md", Data: "# Report\n"}},
})
destinationBackend := fake.New()
writeFakeSharedRootState(t, destinationBackend, "bundle", sharedRootStateWithOwners(t, sourceBundle.Manifest, false))
req := sharedRootRequest(sourceBackend, destinationBackend, sourceBundle, config.ReconciliationModeReplace)
plan, err := Build(context.Background(), req)
if err != nil {
t.Fatalf("Build() error = %v", err)
}
if err := Execute(context.Background(), req, plan); err != nil {
t.Fatalf("Execute() error = %v", err)
}
testutil.AssertFakeFile(t, destinationBackend, "bundle/report.md", "# Report\n")
testutil.AssertFakeFile(t, destinationBackend, "bundle/other/report.md", "old")
destinationState := readFakeSharedRootState(t, destinationBackend, "bundle")
if got, want := len(destinationState.Owners), 2; got != want {
t.Fatalf("owner count = %d, want %d", got, want)
}
if got, want := destinationState.State.Mode, state.StateModeSharedRoot; got != want {
t.Fatalf("state mode = %q, want %q", got, want)
}
if _, ok := destinationState.Owner(state.CurrentOwnerScope("other", "archive")); !ok {
t.Fatal("other owner missing from shared-root state")
}
if _, ok := destinationState.Owner(state.CurrentOwnerScope("reports", "archive")); !ok {
t.Fatal("current owner missing from shared-root state")
}
if got, want := strings.Join(destinationState.AllManagedOutputPaths(), ","), "other/report.md,report.md"; got != want {
t.Fatalf("managed paths = %q, want %q", got, want)
}
}
func TestExecuteSharedRootReplaceDeletesOnlyCurrentOwnerOmittedOutputs(t *testing.T) {
sourceBackend := fake.New()
sourceBundle := testutil.WriteFakeSourceBundle(t, sourceBackend, "bundle", testutil.BundleOptions{
Files: []testutil.SourceFile{{Path: "report.md", Data: "# Report\nNew.\n"}},
})
destinationBackend := fake.New()
existing := sharedRootStateWithOwners(t, sourceBundle.Manifest, true)
writeFakeSharedRootState(t, destinationBackend, "bundle", existing)
req := sharedRootRequest(sourceBackend, destinationBackend, sourceBundle, config.ReconciliationModeReplace)
plan, err := Build(context.Background(), req)
if err != nil {
t.Fatalf("Build() error = %v", err)
}
if err := Execute(context.Background(), req, plan); err != nil {
t.Fatalf("Execute() error = %v", err)
}
testutil.AssertFakeFile(t, destinationBackend, "bundle/report.md", "# Report\nNew.\n")
testutil.AssertFakeMissing(t, destinationBackend, "bundle/old.md")
testutil.AssertFakeFile(t, destinationBackend, "bundle/other/report.md", "old")
destinationState := readFakeSharedRootState(t, destinationBackend, "bundle")
if got, want := strings.Join(destinationState.AllManagedOutputPaths(), ","), "other/report.md,report.md"; got != want {
t.Fatalf("managed paths = %q, want %q", got, want)
}
if !destinationState.CreatedAt.Equal(existing.CreatedAt) {
t.Fatalf("created_at = %s, want %s", destinationState.CreatedAt, existing.CreatedAt)
}
output, ok := findSharedRootOutputForTest(destinationState.Outputs, "report.md")
if !ok {
t.Fatal("report.md missing from shared-root outputs")
}
if !output.CreatedAt.Equal(existing.Outputs[1].CreatedAt) || !output.UpdatedAt.After(existing.Outputs[1].UpdatedAt) {
t.Fatalf("report.md timestamps = created:%s updated:%s, want preserved created and newer updated", output.CreatedAt, output.UpdatedAt)
}
}
func TestExecuteSharedRootMergeRetainsCurrentOwnerOmittedOutputs(t *testing.T) {
sourceBackend := fake.New()
sourceBundle := testutil.WriteFakeSourceBundle(t, sourceBackend, "bundle", testutil.BundleOptions{
Files: []testutil.SourceFile{{Path: "report.md", Data: "# Report\nNew.\n"}},
})
destinationBackend := fake.New()
writeFakeSharedRootState(t, destinationBackend, "bundle", sharedRootStateWithOwners(t, sourceBundle.Manifest, true))
req := sharedRootRequest(sourceBackend, destinationBackend, sourceBundle, config.ReconciliationModeMerge)
plan, err := Build(context.Background(), req)
if err != nil {
t.Fatalf("Build() error = %v", err)
}
if err := Execute(context.Background(), req, plan); err != nil {
t.Fatalf("Execute() error = %v", err)
}
testutil.AssertFakeFile(t, destinationBackend, "bundle/report.md", "# Report\nNew.\n")
testutil.AssertFakeFile(t, destinationBackend, "bundle/old.md", "old")
testutil.AssertFakeFile(t, destinationBackend, "bundle/other/report.md", "old")
destinationState := readFakeSharedRootState(t, destinationBackend, "bundle")
if got, want := strings.Join(destinationState.AllManagedOutputPaths(), ","), "other/report.md,report.md,old.md"; got != want {
t.Fatalf("managed paths = %q, want %q", got, want)
}
}
func TestExecuteSharedRootForceReplaceDeletesOnlyBundlePath(t *testing.T) {
sourceBackend := fake.New()
sourceBundle := testutil.WriteFakeSourceBundle(t, sourceBackend, "bundle", testutil.BundleOptions{
Files: []testutil.SourceFile{{Path: "report.md", Data: "# Report\n"}},
})
destinationBackend := fake.New()
testutil.WriteFakeFile(t, destinationBackend, "bundle/unmanaged.txt", "unmanaged")
testutil.WriteFakeFile(t, destinationBackend, "bundle/nested/old.txt", "old")
testutil.WriteFakeFile(t, destinationBackend, "bundle-sibling/keep.txt", "keep")
req := sharedRootRequest(sourceBackend, destinationBackend, sourceBundle, config.ReconciliationModeReplace)
req.Force = true
plan, err := Build(context.Background(), req)
if err != nil {
t.Fatalf("Build() error = %v", err)
}
if plan.Action != ActionForceReplace {
t.Fatalf("plan action = %s, want force_replace", plan.Action)
}
if err := Execute(context.Background(), req, plan); err != nil {
t.Fatalf("Execute() error = %v", err)
}
testutil.AssertFakeFile(t, destinationBackend, "bundle/report.md", "# Report\n")
testutil.AssertFakeMissing(t, destinationBackend, "bundle/unmanaged.txt")
testutil.AssertFakeMissing(t, destinationBackend, "bundle/nested/old.txt")
testutil.AssertFakeFile(t, destinationBackend, "bundle-sibling/keep.txt", "keep")
destinationState := readFakeSharedRootState(t, destinationBackend, "bundle")
if got, want := len(destinationState.Owners), 1; got != want {
t.Fatalf("owner count = %d, want %d", got, want)
}
}
func sharedRootRequest(sourceBackend, destinationBackend *fake.Backend, sourceBundle bundle.Bundle, reconciliationMode string) Request {
return Request{
PipelineID: "reports",
DestinationID: "archive",
SourceBundle: sourceBundle,
SourceBackend: sourceBackend,
DestinationBackend: destinationBackend,
DestinationBundlePath: sourceBundle.RootRelativePath,
Publish: config.PublishPolicy{Source: true},
State: config.StatePolicy{Mode: config.StateModeSharedRoot},
Reconciliation: config.ReconciliationPolicy{Mode: reconciliationMode},
Transfer: defaultTransfer(),
DistributorVersion: "test",
}
}
func writeFakeSharedRootState(t *testing.T, backend *fake.Backend, relative string, sharedRoot state.SharedRootState) {
t.Helper()
data, err := json.MarshalIndent(sharedRoot, "", " ")
if err != nil {
t.Fatalf("marshal shared-root state: %v", err)
}
statePath, err := storage.StatePath(relative)
if err != nil {
t.Fatalf("state path: %v", err)
}
testutil.WriteFakeFile(t, backend, statePath, string(append(data, '\n')))
for _, output := range sharedRoot.Outputs {
path, err := storage.Join(relative, output.Path)
if err != nil {
t.Fatalf("join output path: %v", err)
}
testutil.WriteFakeFile(t, backend, path, "old")
}
}
func readFakeSharedRootState(t *testing.T, backend *fake.Backend, relative string) state.SharedRootState {
t.Helper()
statePath, err := storage.StatePath(relative)
if err != nil {
t.Fatalf("state path: %v", err)
}
data, err := backend.ReadFile(context.Background(), statePath)
if err != nil {
t.Fatalf("read shared-root state: %v", err)
}
destinationState, err := state.ParseSharedRoot(data)
if err != nil {
t.Fatalf("parse shared-root state: %v", err)
}
return destinationState
}
func findSharedRootOutputForTest(outputs []state.SharedRootOutputFile, path string) (state.SharedRootOutputFile, bool) {
for _, output := range outputs {
if output.Path == path {
return output, true
}
}
return state.SharedRootOutputFile{}, false
}
func sharedRootStateWithOwners(t *testing.T, current bundle.Manifest, includeCurrent bool) state.SharedRootState {
t.Helper()
createdAt := time.Date(2026, 5, 30, 11, 12, 0, 0, time.UTC)
otherManifest := testutil.ValidManifest(testutil.BundleOptions{
ID: "other.source",
Files: []testutil.SourceFile{{Path: "other/report.md", Data: "# Other\n"}},
})
sharedRoot := state.SharedRootState{
SchemaVersion: state.SharedRootSchemaVersion,
DistributorVersion: "test",
CreatedAt: createdAt,
UpdatedAt: createdAt,
State: state.StatePolicy{Mode: state.StateModeSharedRoot},
Owners: []state.OwnerRecord{{
Scope: state.CurrentOwnerScope("other", "archive"),
Reconciliation: state.ReconciliationPolicy{Mode: config.ReconciliationModeReplace},
Source: state.SourceState{Manifest: otherManifest},
}},
Outputs: []state.SharedRootOutputFile{{
Path: "other/report.md",
Kind: state.OutputKindSource,
SourcePath: "other/report.md",
SHA256: otherManifest.Files[0].SHA256,
Size: otherManifest.Files[0].Size,
Owner: state.CurrentOwnerScope("other", "archive"),
SourceID: otherManifest.ID,
SourceDigest: otherManifest.Digest,
SourceCreated: otherManifest.Created,
CreatedAt: createdAt,
UpdatedAt: createdAt,
}},
}
if !includeCurrent {
return sharedRoot
}
older := current
older.Created = older.Created.Add(-time.Hour)
older.Files = append([]bundle.ManifestFile(nil), current.Files...)
older.Files = append(older.Files, bundle.ManifestFile{
Path: "old.md",
SHA256: bundle.FileDigest([]byte("old\n")),
Size: int64(len("old\n")),
})
older.Digest = bundle.BundleDigest(older.Files)
scope := state.CurrentOwnerScope("reports", "archive")
sharedRoot.Owners = append(sharedRoot.Owners, state.OwnerRecord{
Scope: scope,
Reconciliation: state.ReconciliationPolicy{Mode: config.ReconciliationModeReplace},
Source: state.SourceState{Manifest: older},
})
for _, file := range older.Files {
sharedRoot.Outputs = append(sharedRoot.Outputs, state.SharedRootOutputFile{
Path: file.Path,
Kind: state.OutputKindSource,
SourcePath: file.Path,
SHA256: file.SHA256,
Size: file.Size,
Owner: scope,
SourceID: older.ID,
SourceDigest: older.Digest,
SourceCreated: older.Created,
CreatedAt: createdAt,
UpdatedAt: createdAt,
})
}
return sharedRoot
}
func sharedRootOutputPathList(outputs []state.SharedRootOutputFile) string {
paths := make([]string, 0, len(outputs))
for _, output := range outputs {
paths = append(paths, output.Path)
}
return strings.Join(paths, ",")
}

422
internal/state/catalog.go Normal file
View File

@@ -0,0 +1,422 @@
package state
import (
"bytes"
"encoding/json"
"fmt"
"io"
"time"
"gitea.maximumdirect.net/eric/distributor/internal/bundle"
"gitea.maximumdirect.net/eric/distributor/internal/config"
"gitea.maximumdirect.net/eric/distributor/internal/link"
"gitea.maximumdirect.net/eric/distributor/internal/storage"
)
type CatalogState struct {
SchemaVersion int
DistributorVersion string
CreatedAt time.Time
UpdatedAt time.Time
State StatePolicy
Outputs []CatalogOutputFile
}
type CatalogSourceIdentity struct {
ID string
Digest string
Created time.Time
}
type CatalogOutputFile struct {
Path string
PipelineID string
DestinationID string
Source CatalogSourceIdentity
Kind string
SourcePath string
Transform string
URL string
SHA256 string
Size int64
CreatedAt time.Time
UpdatedAt time.Time
}
type rawCatalogState struct {
SchemaVersion *int `json:"schema_version"`
DistributorVersion string `json:"distributor_version"`
CreatedAt *string `json:"created_at"`
UpdatedAt *string `json:"updated_at"`
State *rawStatePolicy `json:"state"`
Outputs []rawCatalogOutput `json:"outputs"`
}
type rawCatalogOutput struct {
Path *string `json:"path"`
PipelineID *string `json:"pipeline_id"`
DestinationID *string `json:"destination_id"`
Source *rawCatalogSourceIdentity `json:"source"`
Kind *string `json:"kind"`
SourcePath *string `json:"source_path"`
Transform *string `json:"transform"`
URL *string `json:"url"`
SHA256 *string `json:"sha256"`
Size *int64 `json:"size"`
CreatedAt *string `json:"created_at"`
UpdatedAt *string `json:"updated_at"`
}
type rawCatalogSourceIdentity struct {
ID *string `json:"id"`
Digest *string `json:"digest"`
Created *string `json:"created"`
}
func ParseCatalog(data []byte) (CatalogState, error) {
decoder := json.NewDecoder(bytes.NewReader(data))
decoder.DisallowUnknownFields()
var raw rawCatalogState
if err := decoder.Decode(&raw); err != nil {
return CatalogState{}, fmt.Errorf("parse distributor state: %w", err)
}
var extra any
if err := decoder.Decode(&extra); err != io.EOF {
return CatalogState{}, fmt.Errorf("parse distributor state: trailing data")
}
state, err := parseCatalogRaw(raw)
if err != nil {
return CatalogState{}, err
}
if err := ValidateCatalog(state); err != nil {
return CatalogState{}, err
}
return state, nil
}
func parseCatalogRaw(raw rawCatalogState) (CatalogState, error) {
if raw.SchemaVersion == nil {
return CatalogState{}, fmt.Errorf("state schema_version is required")
}
state := CatalogState{
SchemaVersion: *raw.SchemaVersion,
DistributorVersion: raw.DistributorVersion,
}
if state.SchemaVersion != CatalogSchemaVersion {
return CatalogState{}, fmt.Errorf("state schema_version must be %d", CatalogSchemaVersion)
}
createdAt, err := parseRequiredTime("state created_at", raw.CreatedAt)
if err != nil {
return CatalogState{}, err
}
updatedAt, err := parseRequiredTime("state updated_at", raw.UpdatedAt)
if err != nil {
return CatalogState{}, err
}
state.CreatedAt = createdAt
state.UpdatedAt = updatedAt
if raw.State == nil || raw.State.Mode == "" {
return CatalogState{}, fmt.Errorf("state state.mode is required")
}
state.State.Mode = raw.State.Mode
if raw.Outputs == nil {
return CatalogState{}, fmt.Errorf("state outputs is required")
}
outputs, err := parseCatalogOutputs(raw.Outputs)
if err != nil {
return CatalogState{}, err
}
state.Outputs = outputs
return state, nil
}
func parseCatalogOutputs(rawOutputs []rawCatalogOutput) ([]CatalogOutputFile, error) {
outputs := make([]CatalogOutputFile, 0, len(rawOutputs))
for index, raw := range rawOutputs {
output, err := parseCatalogOutput(index, raw)
if err != nil {
return nil, err
}
outputs = append(outputs, output)
}
return outputs, nil
}
func parseCatalogOutput(index int, raw rawCatalogOutput) (CatalogOutputFile, error) {
if raw.Path == nil || *raw.Path == "" {
return CatalogOutputFile{}, fmt.Errorf("state outputs[%d].path is required", index)
}
if raw.PipelineID == nil || *raw.PipelineID == "" {
return CatalogOutputFile{}, fmt.Errorf("state outputs[%d].pipeline_id is required", index)
}
if raw.DestinationID == nil || *raw.DestinationID == "" {
return CatalogOutputFile{}, fmt.Errorf("state outputs[%d].destination_id is required", index)
}
source, err := parseCatalogSourceIdentity(index, raw.Source)
if err != nil {
return CatalogOutputFile{}, err
}
if raw.Kind == nil || *raw.Kind == "" {
return CatalogOutputFile{}, fmt.Errorf("state outputs[%d].kind is required", index)
}
switch *raw.Kind {
case OutputKindSource:
if raw.SourcePath != nil {
return CatalogOutputFile{}, fmt.Errorf("state outputs[%d].source_path is only valid for generated output", index)
}
if raw.Transform != nil {
return CatalogOutputFile{}, fmt.Errorf("state outputs[%d].transform is only valid for generated output", index)
}
case OutputKindGenerated:
if raw.SourcePath == nil || *raw.SourcePath == "" {
return CatalogOutputFile{}, fmt.Errorf("state outputs[%d].source_path is required for generated output", index)
}
if raw.Transform == nil || *raw.Transform == "" {
return CatalogOutputFile{}, fmt.Errorf("state outputs[%d].transform is required for generated output", index)
}
}
if raw.SHA256 == nil || *raw.SHA256 == "" {
return CatalogOutputFile{}, fmt.Errorf("state outputs[%d].sha256 is required", index)
}
if raw.Size == nil {
return CatalogOutputFile{}, fmt.Errorf("state outputs[%d].size is required", index)
}
createdAt, err := parseRequiredTime(fmt.Sprintf("state outputs[%d].created_at", index), raw.CreatedAt)
if err != nil {
return CatalogOutputFile{}, err
}
updatedAt, err := parseRequiredTime(fmt.Sprintf("state outputs[%d].updated_at", index), raw.UpdatedAt)
if err != nil {
return CatalogOutputFile{}, err
}
output := CatalogOutputFile{
Path: *raw.Path,
PipelineID: *raw.PipelineID,
DestinationID: *raw.DestinationID,
Source: source,
Kind: *raw.Kind,
SHA256: *raw.SHA256,
Size: *raw.Size,
CreatedAt: createdAt,
UpdatedAt: updatedAt,
}
if raw.SourcePath != nil {
output.SourcePath = *raw.SourcePath
}
if raw.Transform != nil {
output.Transform = *raw.Transform
}
if raw.URL != nil {
if *raw.URL == "" {
return CatalogOutputFile{}, fmt.Errorf("state outputs[%d].url must not be empty", index)
}
output.URL = *raw.URL
}
return output, nil
}
func parseCatalogSourceIdentity(index int, raw *rawCatalogSourceIdentity) (CatalogSourceIdentity, error) {
if raw == nil {
return CatalogSourceIdentity{}, fmt.Errorf("state outputs[%d].source is required", index)
}
if raw.ID == nil || *raw.ID == "" {
return CatalogSourceIdentity{}, fmt.Errorf("state outputs[%d].source.id is required", index)
}
if raw.Digest == nil || *raw.Digest == "" {
return CatalogSourceIdentity{}, fmt.Errorf("state outputs[%d].source.digest is required", index)
}
created, err := parseRequiredTime(fmt.Sprintf("state outputs[%d].source.created", index), raw.Created)
if err != nil {
return CatalogSourceIdentity{}, err
}
return CatalogSourceIdentity{
ID: *raw.ID,
Digest: *raw.Digest,
Created: created,
}, nil
}
func (s CatalogState) CreatedAtString() string {
return s.CreatedAt.UTC().Format(time.RFC3339)
}
func (s CatalogState) UpdatedAtString() string {
return s.UpdatedAt.UTC().Format(time.RFC3339)
}
func (s CatalogSourceIdentity) CreatedString() string {
return s.Created.UTC().Format(time.RFC3339)
}
func (o CatalogOutputFile) CreatedAtString() string {
return o.CreatedAt.UTC().Format(time.RFC3339)
}
func (o CatalogOutputFile) UpdatedAtString() string {
return o.UpdatedAt.UTC().Format(time.RFC3339)
}
func (s CatalogState) MarshalJSON() ([]byte, error) {
type stateJSON struct {
SchemaVersion int `json:"schema_version"`
DistributorVersion string `json:"distributor_version,omitempty"`
CreatedAt string `json:"created_at"`
UpdatedAt string `json:"updated_at"`
State StatePolicy `json:"state"`
Outputs []CatalogOutputFile `json:"outputs"`
}
return json.Marshal(stateJSON{
SchemaVersion: s.SchemaVersion,
DistributorVersion: s.DistributorVersion,
CreatedAt: s.CreatedAtString(),
UpdatedAt: s.UpdatedAtString(),
State: s.State,
Outputs: s.Outputs,
})
}
func (s CatalogSourceIdentity) MarshalJSON() ([]byte, error) {
type sourceJSON struct {
ID string `json:"id"`
Digest string `json:"digest"`
Created string `json:"created"`
}
return json.Marshal(sourceJSON{
ID: s.ID,
Digest: s.Digest,
Created: s.CreatedString(),
})
}
func (o CatalogOutputFile) MarshalJSON() ([]byte, error) {
type outputJSON struct {
Path string `json:"path"`
PipelineID string `json:"pipeline_id"`
DestinationID string `json:"destination_id"`
Source CatalogSourceIdentity `json:"source"`
Kind string `json:"kind"`
SourcePath string `json:"source_path,omitempty"`
Transform string `json:"transform,omitempty"`
URL string `json:"url,omitempty"`
SHA256 string `json:"sha256"`
Size int64 `json:"size"`
CreatedAt string `json:"created_at"`
UpdatedAt string `json:"updated_at"`
}
return json.Marshal(outputJSON{
Path: o.Path,
PipelineID: o.PipelineID,
DestinationID: o.DestinationID,
Source: o.Source,
Kind: o.Kind,
SourcePath: o.SourcePath,
Transform: o.Transform,
URL: o.URL,
SHA256: o.SHA256,
Size: o.Size,
CreatedAt: o.CreatedAtString(),
UpdatedAt: o.UpdatedAtString(),
})
}
func ValidateCatalog(s CatalogState) error {
if s.SchemaVersion != CatalogSchemaVersion {
return fmt.Errorf("state schema_version must be %d", CatalogSchemaVersion)
}
if s.CreatedAt.IsZero() {
return fmt.Errorf("state created_at is required")
}
if s.UpdatedAt.IsZero() {
return fmt.Errorf("state updated_at is required")
}
if s.State.Mode != StateModeCatalog {
return fmt.Errorf("state state.mode must be %s", StateModeCatalog)
}
if s.Outputs == nil {
return fmt.Errorf("state outputs is required")
}
seenPaths := make(map[string]struct{}, len(s.Outputs))
for index, output := range s.Outputs {
if err := validateCatalogOutput(index, output); err != nil {
return err
}
if _, exists := seenPaths[output.Path]; exists {
return fmt.Errorf("state outputs[%d].path duplicates %q", index, output.Path)
}
seenPaths[output.Path] = struct{}{}
}
return nil
}
func validateCatalogOutput(index int, output CatalogOutputFile) error {
if err := storage.ValidatePath(output.Path); err != nil {
return fmt.Errorf("state outputs[%d].path: %w", index, err)
}
if output.PipelineID == "" {
return fmt.Errorf("state outputs[%d].pipeline_id is required", index)
}
if !config.IsSlugLikeID(output.PipelineID) {
return fmt.Errorf("state outputs[%d].pipeline_id must be a slug-like identifier", index)
}
if output.DestinationID == "" {
return fmt.Errorf("state outputs[%d].destination_id is required", index)
}
if !config.IsSlugLikeID(output.DestinationID) {
return fmt.Errorf("state outputs[%d].destination_id must be a slug-like identifier", index)
}
if err := validateCatalogSourceIdentity(index, output.Source); err != nil {
return err
}
switch output.Kind {
case OutputKindSource:
if output.SourcePath != "" {
return fmt.Errorf("state outputs[%d].source_path is only valid for generated output", index)
}
if output.Transform != "" {
return fmt.Errorf("state outputs[%d].transform is only valid for generated output", index)
}
case OutputKindGenerated:
if output.SourcePath == "" {
return fmt.Errorf("state outputs[%d].source_path is required for generated output", index)
}
if err := storage.ValidatePath(output.SourcePath); err != nil {
return fmt.Errorf("state outputs[%d].source_path: %w", index, err)
}
if output.Transform == "" {
return fmt.Errorf("state outputs[%d].transform is required for generated output", index)
}
default:
return fmt.Errorf("state outputs[%d].kind must be source or generated", index)
}
if output.URL != "" {
if err := link.ValidateHTTPURL(output.URL); err != nil {
return fmt.Errorf("state outputs[%d].url: %w", index, err)
}
}
if err := bundle.ValidateDigest(output.SHA256); err != nil {
return fmt.Errorf("state outputs[%d].sha256: %w", index, err)
}
if output.Size < 0 {
return fmt.Errorf("state outputs[%d].size must be non-negative", index)
}
if output.CreatedAt.IsZero() {
return fmt.Errorf("state outputs[%d].created_at is required", index)
}
if output.UpdatedAt.IsZero() {
return fmt.Errorf("state outputs[%d].updated_at is required", index)
}
return nil
}
func validateCatalogSourceIdentity(index int, source CatalogSourceIdentity) error {
if source.ID == "" {
return fmt.Errorf("state outputs[%d].source.id is required", index)
}
if err := bundle.ValidateDigest(source.Digest); err != nil {
return fmt.Errorf("state outputs[%d].source.digest: %w", index, err)
}
if source.Created.IsZero() {
return fmt.Errorf("state outputs[%d].source.created is required", index)
}
return nil
}

View File

@@ -0,0 +1,361 @@
package state
import (
"encoding/json"
"strings"
"testing"
"time"
)
func TestParseCatalogState(t *testing.T) {
state, err := ParseCatalog([]byte(validCatalogStateJSON(t)))
if err != nil {
t.Fatalf("ParseCatalog() error = %v", err)
}
if got, want := state.SchemaVersion, CatalogSchemaVersion; got != want {
t.Fatalf("schema version = %d, want %d", got, want)
}
if got, want := state.CreatedAtString(), "2026-06-19T12:00:00Z"; got != want {
t.Fatalf("created_at = %q, want %q", got, want)
}
if got, want := state.UpdatedAtString(), "2026-06-19T12:05:00Z"; got != want {
t.Fatalf("updated_at = %q, want %q", got, want)
}
if got, want := state.State.Mode, StateModeCatalog; got != want {
t.Fatalf("state mode = %q, want %q", got, want)
}
if got, want := len(state.Outputs), 2; got != want {
t.Fatalf("output count = %d, want %d", got, want)
}
sourceOutput := state.Outputs[0]
if sourceOutput.SourcePath != "" || sourceOutput.Transform != "" {
t.Fatalf("source output source_path=%q transform=%q, want omitted", sourceOutput.SourcePath, sourceOutput.Transform)
}
generatedOutput := state.Outputs[1]
if generatedOutput.SourcePath != "report.md" || generatedOutput.Transform != "markdown_to_html" {
t.Fatalf("generated output source_path=%q transform=%q", generatedOutput.SourcePath, generatedOutput.Transform)
}
if got, want := generatedOutput.Source.CreatedString(), "2026-05-30T11:10:00Z"; got != want {
t.Fatalf("source created = %q, want %q", got, want)
}
}
func TestCatalogMarshalIsDeterministic(t *testing.T) {
data, err := json.Marshal(validCatalogState(t))
if err != nil {
t.Fatalf("Marshal() error = %v", err)
}
want := `{"schema_version":4,"distributor_version":"dev","created_at":"2026-06-19T12:00:00Z","updated_at":"2026-06-19T12:05:00Z","state":{"mode":"catalog"},"outputs":[{"path":"report.md","pipeline_id":"reports","destination_id":"archive","source":{"id":"weather.daily.brentwood.2026-05-30","digest":"sha256:099b205780d2b050024868399961b05731729a548d5d6329c7b06a6740dd75fe","created":"2026-05-30T11:10:00Z"},"kind":"source","sha256":"sha256:3640fd37140ee4d2e0e93e78834f232ea67a50e7bc6279203690cc7de1975fa6","size":16,"created_at":"2026-06-19T12:00:00Z","updated_at":"2026-06-19T12:05:00Z"},{"path":"report.html","pipeline_id":"reports","destination_id":"html","source":{"id":"weather.daily.brentwood.2026-05-30","digest":"sha256:099b205780d2b050024868399961b05731729a548d5d6329c7b06a6740dd75fe","created":"2026-05-30T11:10:00Z"},"kind":"generated","source_path":"report.md","transform":"markdown_to_html","url":"https://reports.example.com/report.html","sha256":"sha256:aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa","size":128,"created_at":"2026-06-19T12:00:00Z","updated_at":"2026-06-19T12:05:00Z"}]}`
if string(data) != want {
t.Fatalf("json = %s, want %s", data, want)
}
}
func TestParseDocumentHandlesCatalogAndSupersededLegacy(t *testing.T) {
catalog, err := ParseDocument([]byte(validCatalogStateJSON(t)))
if err != nil {
t.Fatalf("ParseDocument(catalog) error = %v", err)
}
if catalog.Catalog == nil || catalog.SingleOwner != nil || catalog.SharedRoot != nil || catalog.SupersededLegacy != nil {
t.Fatalf("catalog document = %#v", catalog)
}
tests := map[string]string{
"schema 1": legacyStateJSON(t),
"schema 2": validStateJSON(t),
"schema 3": validSharedRootStateJSON(t),
}
for name, body := range tests {
t.Run(name, func(t *testing.T) {
document, err := ParseDocument([]byte(body))
if err != nil {
t.Fatalf("ParseDocument() error = %v", err)
}
if document.SupersededLegacy == nil || document.Catalog != nil || document.SingleOwner != nil || document.SharedRoot != nil {
t.Fatalf("document = %#v, want superseded legacy only", document)
}
if document.SupersededLegacy.SchemaVersion < legacySchemaVersion || document.SupersededLegacy.SchemaVersion >= CatalogSchemaVersion {
t.Fatalf("legacy schema version = %d, want 1 through 3", document.SupersededLegacy.SchemaVersion)
}
})
}
}
func TestParseDocumentRejectsUnsupportedFutureSchema(t *testing.T) {
body := strings.Replace(validCatalogStateJSON(t), `"schema_version": 4`, `"schema_version": 5`, 1)
_, err := ParseDocument([]byte(body))
assertStateErrorContains(t, err, "schema_version 5 is unsupported")
}
func TestParseDocumentRejectsTrailingData(t *testing.T) {
_, err := ParseDocument([]byte(validCatalogStateJSON(t) + "\n{}"))
assertStateErrorContains(t, err, "trailing data")
}
func TestParseCatalogRejectsMissingFields(t *testing.T) {
tests := map[string]func(map[string]any){
"schema_version": func(document map[string]any) {
delete(document, "schema_version")
},
"created_at": func(document map[string]any) {
delete(document, "created_at")
},
"updated_at": func(document map[string]any) {
delete(document, "updated_at")
},
"state": func(document map[string]any) {
delete(document, "state")
},
"outputs": func(document map[string]any) {
delete(document, "outputs")
},
"path": func(document map[string]any) {
delete(firstCatalogOutput(document), "path")
},
"pipeline_id": func(document map[string]any) {
delete(firstCatalogOutput(document), "pipeline_id")
},
"destination_id": func(document map[string]any) {
delete(firstCatalogOutput(document), "destination_id")
},
"source": func(document map[string]any) {
delete(firstCatalogOutput(document), "source")
},
"source id": func(document map[string]any) {
delete(firstCatalogSource(document), "id")
},
"source digest": func(document map[string]any) {
delete(firstCatalogSource(document), "digest")
},
"source created": func(document map[string]any) {
delete(firstCatalogSource(document), "created")
},
"kind": func(document map[string]any) {
delete(firstCatalogOutput(document), "kind")
},
"sha256": func(document map[string]any) {
delete(firstCatalogOutput(document), "sha256")
},
"size": func(document map[string]any) {
delete(firstCatalogOutput(document), "size")
},
}
for name, mutate := range tests {
t.Run(name, func(t *testing.T) {
document := catalogStateObject(t)
mutate(document)
_, err := ParseCatalog(mustMarshalCatalogObject(t, document))
assertStateErrorContains(t, err, "required")
})
}
}
func TestParseCatalogRejectsMalformedTimestamps(t *testing.T) {
tests := map[string]func(string) string{
"created_at": func(body string) string {
return strings.Replace(body, `"created_at": "2026-06-19T12:00:00Z"`, `"created_at": "June 19"`, 1)
},
"updated_at": func(body string) string {
return strings.Replace(body, `"updated_at": "2026-06-19T12:05:00Z"`, `"updated_at": "June 19"`, 1)
},
"source created": func(body string) string {
return strings.Replace(body, `"created": "2026-05-30T11:10:00Z"`, `"created": "May 30"`, 1)
},
"output created_at": func(body string) string {
return strings.Replace(body, ` "created_at": "2026-06-19T12:00:00Z"`, ` "created_at": "June 19"`, 1)
},
"output updated_at": func(body string) string {
return strings.Replace(body, ` "updated_at": "2026-06-19T12:05:00Z"`, ` "updated_at": "June 19"`, 1)
},
}
for name, mutate := range tests {
t.Run(name, func(t *testing.T) {
_, err := ParseCatalog([]byte(mutate(validCatalogStateJSON(t))))
assertStateErrorContains(t, err, "RFC3339")
})
}
}
func TestValidateCatalogRejectsInvalidOutputRecords(t *testing.T) {
tests := map[string]func(*CatalogState){
"duplicate path": func(s *CatalogState) {
s.Outputs[1].Path = s.Outputs[0].Path
},
"invalid output path": func(s *CatalogState) {
s.Outputs[0].Path = "../report.md"
},
"invalid pipeline id": func(s *CatalogState) {
s.Outputs[0].PipelineID = ".reports"
},
"invalid destination id": func(s *CatalogState) {
s.Outputs[0].DestinationID = ".archive"
},
"missing source id": func(s *CatalogState) {
s.Outputs[0].Source.ID = ""
},
"invalid source digest": func(s *CatalogState) {
s.Outputs[0].Source.Digest = "SHA256:099b205780d2b050024868399961b05731729a548d5d6329c7b06a6740dd75fe"
},
"missing source created": func(s *CatalogState) {
s.Outputs[0].Source.Created = time.Time{}
},
"invalid kind": func(s *CatalogState) {
s.Outputs[0].Kind = "document"
},
"generated missing source path": func(s *CatalogState) {
s.Outputs[1].SourcePath = ""
},
"generated invalid source path": func(s *CatalogState) {
s.Outputs[1].SourcePath = "../report.md"
},
"generated missing transform": func(s *CatalogState) {
s.Outputs[1].Transform = ""
},
"source output source path": func(s *CatalogState) {
s.Outputs[0].SourcePath = "report.md"
},
"source output transform": func(s *CatalogState) {
s.Outputs[0].Transform = "markdown_to_html"
},
"invalid output digest": func(s *CatalogState) {
s.Outputs[0].SHA256 = "SHA256:3640fd37140ee4d2e0e93e78834f232ea67a50e7bc6279203690cc7de1975fa6"
},
"negative size": func(s *CatalogState) {
s.Outputs[0].Size = -1
},
"invalid url": func(s *CatalogState) {
s.Outputs[1].URL = "file:///tmp/report.html"
},
"missing created at": func(s *CatalogState) {
s.Outputs[0].CreatedAt = time.Time{}
},
"missing updated at": func(s *CatalogState) {
s.Outputs[0].UpdatedAt = time.Time{}
},
}
for name, mutate := range tests {
t.Run(name, func(t *testing.T) {
state := validCatalogState(t)
mutate(&state)
if err := ValidateCatalog(state); err == nil {
t.Fatal("ValidateCatalog() error = nil, want error")
}
})
}
}
func TestParseCatalogRejectsForbiddenFields(t *testing.T) {
tests := map[string]string{
"owners": `"owners": [],`,
"sources": `"sources": [],`,
"workflow": `"workflow": "additive",`,
"source": `"source": {"manifest": {}},`,
"manifest": `"manifest": {},`,
"pipeline_id": `"pipeline_id": "reports",`,
"destination_id": `"destination_id": "archive",`,
"published_at": `"published_at": "2026-06-19T12:00:00Z",`,
}
for name, field := range tests {
t.Run(name, func(t *testing.T) {
body := strings.Replace(validCatalogStateJSON(t), `"created_at":`, field+"\n "+`"created_at":`, 1)
_, err := ParseCatalog([]byte(body))
assertStateErrorContains(t, err, "unknown field")
})
}
}
func TestParseCatalogRejectsForbiddenOutputFieldsForSourceOutput(t *testing.T) {
tests := map[string]string{
"source_path": `"source_path": "report.md",`,
"transform": `"transform": "markdown_to_html",`,
"empty url": `"url": "",`,
}
for name, field := range tests {
t.Run(name, func(t *testing.T) {
body := strings.Replace(validCatalogStateJSON(t), `"kind": "source",`, `"kind": "source",`+"\n "+field, 1)
_, err := ParseCatalog([]byte(body))
if err == nil {
t.Fatal("ParseCatalog() error = nil, want error")
}
})
}
}
func validCatalogStateJSON(t *testing.T) string {
t.Helper()
data, err := json.MarshalIndent(validCatalogState(t), "", " ")
if err != nil {
t.Fatalf("marshal catalog state: %v", err)
}
return string(data)
}
func catalogStateObject(t *testing.T) map[string]any {
t.Helper()
var document map[string]any
if err := json.Unmarshal([]byte(validCatalogStateJSON(t)), &document); err != nil {
t.Fatalf("unmarshal catalog state: %v", err)
}
return document
}
func firstCatalogOutput(document map[string]any) map[string]any {
outputs := document["outputs"].([]any)
return outputs[0].(map[string]any)
}
func firstCatalogSource(document map[string]any) map[string]any {
return firstCatalogOutput(document)["source"].(map[string]any)
}
func mustMarshalCatalogObject(t *testing.T, document map[string]any) []byte {
t.Helper()
data, err := json.Marshal(document)
if err != nil {
t.Fatalf("marshal catalog object: %v", err)
}
return data
}
func validCatalogState(t *testing.T) CatalogState {
t.Helper()
manifest := validManifest(t)
createdAt := time.Date(2026, 6, 19, 12, 0, 0, 0, time.UTC)
updatedAt := time.Date(2026, 6, 19, 12, 5, 0, 0, time.UTC)
source := CatalogSourceIdentity{
ID: manifest.ID,
Digest: manifest.Digest,
Created: manifest.Created,
}
return CatalogState{
SchemaVersion: CatalogSchemaVersion,
DistributorVersion: "dev",
CreatedAt: createdAt,
UpdatedAt: updatedAt,
State: StatePolicy{Mode: StateModeCatalog},
Outputs: []CatalogOutputFile{{
Path: "report.md",
PipelineID: "reports",
DestinationID: "archive",
Source: source,
Kind: OutputKindSource,
SHA256: manifest.Files[0].SHA256,
Size: manifest.Files[0].Size,
CreatedAt: createdAt,
UpdatedAt: updatedAt,
}, {
Path: "report.html",
PipelineID: "reports",
DestinationID: "html",
Source: source,
Kind: OutputKindGenerated,
SourcePath: "report.md",
Transform: "markdown_to_html",
URL: "https://reports.example.com/report.html",
SHA256: "sha256:aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
Size: 128,
CreatedAt: createdAt,
UpdatedAt: updatedAt,
}},
}
}

View File

@@ -23,6 +23,8 @@ const (
type DestinationStatus struct {
State *DistributorState
SharedRoot *SharedRootState
Catalog *CatalogState
SupersededLegacy *SupersededLegacyState
StateErr error
HasContents bool
}
@@ -30,37 +32,75 @@ type DestinationStatus struct {
type Comparison struct {
Outcome Outcome
Reason string
Detail ComparisonDetail
}
type ComparisonDetailKind string
const (
ComparisonDetailNone ComparisonDetailKind = ""
ComparisonDetailInvalidState ComparisonDetailKind = "invalid_state"
ComparisonDetailUnmanagedContent ComparisonDetailKind = "unmanaged_content"
ComparisonDetailPipelineIDMismatch ComparisonDetailKind = "pipeline_id_mismatch"
ComparisonDetailDestinationIDMismatch ComparisonDetailKind = "destination_id_mismatch"
ComparisonDetailDifferentSourceID ComparisonDetailKind = "different_source_id"
ComparisonDetailSameCreatedDigestConflict ComparisonDetailKind = "same_created_digest_conflict"
ComparisonDetailDestinationNewer ComparisonDetailKind = "destination_newer"
ComparisonDetailSharedRootOwnerAbsent ComparisonDetailKind = "shared_root_owner_absent"
ComparisonDetailSharedRootOutputOwner ComparisonDetailKind = "shared_root_output_owner_conflict"
)
type ComparisonDetail struct {
Kind ComparisonDetailKind
CurrentPipelineID string
CurrentDestinationID string
DestinationPipelineID string
DestinationDestinationID string
CurrentSourceID string
DestinationSourceID string
CurrentSourceDigest string
DestinationSourceDigest string
Path string
CurrentOwner OwnerScope
ConflictingOwner OwnerScope
}
func CompareSharedRootOwner(source bundle.Manifest, scope OwnerScope, status DestinationStatus) Comparison {
if status.StateErr != nil {
return Comparison{Outcome: OutcomeInvalidState, Reason: status.StateErr.Error()}
return Comparison{Outcome: OutcomeInvalidState, Reason: status.StateErr.Error(), Detail: ComparisonDetail{Kind: ComparisonDetailInvalidState}}
}
if status.SharedRoot != nil {
if err := ValidateSharedRoot(*status.SharedRoot); err != nil {
return Comparison{Outcome: OutcomeInvalidState, Reason: err.Error()}
return Comparison{Outcome: OutcomeInvalidState, Reason: err.Error(), Detail: ComparisonDetail{Kind: ComparisonDetailInvalidState}}
}
owner, ok := status.SharedRoot.Owner(scope)
if !ok {
return Comparison{Outcome: OutcomeDestinationAbsent, Reason: fmt.Sprintf("destination owner %s/%s is absent", scope.PipelineID, scope.DestinationID)}
return Comparison{
Outcome: OutcomeDestinationAbsent,
Reason: fmt.Sprintf("destination owner %s/%s is absent", scope.PipelineID, scope.DestinationID),
Detail: ComparisonDetail{
Kind: ComparisonDetailSharedRootOwnerAbsent,
CurrentOwner: scope,
},
}
}
return compareManifests(source, owner.Source.Manifest)
}
if status.State != nil {
destinationState := *status.State
if err := Validate(destinationState); err != nil {
return Comparison{Outcome: OutcomeInvalidState, Reason: err.Error()}
return Comparison{Outcome: OutcomeInvalidState, Reason: err.Error(), Detail: ComparisonDetail{Kind: ComparisonDetailInvalidState}}
}
if destinationState.PipelineID != scope.PipelineID {
return Comparison{Outcome: OutcomeIdentityMismatch, Reason: fmt.Sprintf("pipeline id %q does not match %q", destinationState.PipelineID, scope.PipelineID)}
return pipelineIDMismatchComparison(destinationState.PipelineID, scope.PipelineID)
}
if destinationState.DestinationID != scope.DestinationID {
return Comparison{Outcome: OutcomeIdentityMismatch, Reason: fmt.Sprintf("destination id %q does not match %q", destinationState.DestinationID, scope.DestinationID)}
return destinationIDMismatchComparison(destinationState.DestinationID, scope.DestinationID)
}
return compareManifests(source, destinationState.Source.Manifest)
}
if status.HasContents {
return Comparison{Outcome: OutcomeDestinationUnmanaged, Reason: "destination has content but no distributor state"}
return Comparison{Outcome: OutcomeDestinationUnmanaged, Reason: "destination has content but no distributor state", Detail: ComparisonDetail{Kind: ComparisonDetailUnmanagedContent}}
}
return Comparison{Outcome: OutcomeDestinationAbsent, Reason: "destination state is absent"}
}
@@ -70,45 +110,95 @@ func compareManifests(source, destination bundle.Manifest) Comparison {
return Comparison{Outcome: OutcomeSameSource, Reason: "destination source manifest matches source"}
}
if destination.ID != source.ID {
return Comparison{Outcome: OutcomeDifferentSourceConflict, Reason: "destination source id differs from source"}
return Comparison{
Outcome: OutcomeDifferentSourceConflict,
Reason: "destination source id differs from source",
Detail: ComparisonDetail{
Kind: ComparisonDetailDifferentSourceID,
CurrentSourceID: source.ID,
DestinationSourceID: destination.ID,
},
}
}
if destination.Created.Before(source.Created) {
return Comparison{Outcome: OutcomeDestinationOlder, Reason: "destination source is older than source"}
}
if destination.Created.After(source.Created) {
return Comparison{Outcome: OutcomeDestinationNewer, Reason: "destination source is newer than source"}
return Comparison{
Outcome: OutcomeDestinationNewer,
Reason: "destination source is newer than source",
Detail: ComparisonDetail{
Kind: ComparisonDetailDestinationNewer,
CurrentSourceID: source.ID,
DestinationSourceID: destination.ID,
},
}
}
if destination.Digest != source.Digest {
return Comparison{Outcome: OutcomeSameCreatedConflict, Reason: "destination source has same id and created time but different digest"}
return Comparison{
Outcome: OutcomeSameCreatedConflict,
Reason: "destination source has same id and created time but different digest",
Detail: ComparisonDetail{
Kind: ComparisonDetailSameCreatedDigestConflict,
CurrentSourceID: source.ID,
DestinationSourceID: destination.ID,
CurrentSourceDigest: source.Digest,
DestinationSourceDigest: destination.Digest,
},
}
return Comparison{Outcome: OutcomeInvalidState, Reason: "destination source differs from source without a supported comparison outcome"}
}
return Comparison{Outcome: OutcomeInvalidState, Reason: "destination source differs from source without a supported comparison outcome", Detail: ComparisonDetail{Kind: ComparisonDetailInvalidState}}
}
func Compare(source bundle.Manifest, pipelineID, destinationID string, status DestinationStatus) Comparison {
if status.StateErr != nil {
return Comparison{Outcome: OutcomeInvalidState, Reason: status.StateErr.Error()}
return Comparison{Outcome: OutcomeInvalidState, Reason: status.StateErr.Error(), Detail: ComparisonDetail{Kind: ComparisonDetailInvalidState}}
}
if status.State == nil {
if status.HasContents {
return Comparison{Outcome: OutcomeDestinationUnmanaged, Reason: "destination has content but no distributor state"}
return Comparison{Outcome: OutcomeDestinationUnmanaged, Reason: "destination has content but no distributor state", Detail: ComparisonDetail{Kind: ComparisonDetailUnmanagedContent}}
}
return Comparison{Outcome: OutcomeDestinationAbsent, Reason: "destination state is absent"}
}
destinationState := *status.State
if err := Validate(destinationState); err != nil {
return Comparison{Outcome: OutcomeInvalidState, Reason: err.Error()}
return Comparison{Outcome: OutcomeInvalidState, Reason: err.Error(), Detail: ComparisonDetail{Kind: ComparisonDetailInvalidState}}
}
if destinationState.PipelineID != pipelineID {
return Comparison{Outcome: OutcomeIdentityMismatch, Reason: fmt.Sprintf("pipeline id %q does not match %q", destinationState.PipelineID, pipelineID)}
return pipelineIDMismatchComparison(destinationState.PipelineID, pipelineID)
}
if destinationState.DestinationID != destinationID {
return Comparison{Outcome: OutcomeIdentityMismatch, Reason: fmt.Sprintf("destination id %q does not match %q", destinationState.DestinationID, destinationID)}
return destinationIDMismatchComparison(destinationState.DestinationID, destinationID)
}
return compareManifests(source, destinationState.Source.Manifest)
}
func pipelineIDMismatchComparison(destinationPipelineID, currentPipelineID string) Comparison {
return Comparison{
Outcome: OutcomeIdentityMismatch,
Reason: fmt.Sprintf("pipeline id %q does not match %q", destinationPipelineID, currentPipelineID),
Detail: ComparisonDetail{
Kind: ComparisonDetailPipelineIDMismatch,
CurrentPipelineID: currentPipelineID,
DestinationPipelineID: destinationPipelineID,
},
}
}
func destinationIDMismatchComparison(destinationDestinationID, currentDestinationID string) Comparison {
return Comparison{
Outcome: OutcomeIdentityMismatch,
Reason: fmt.Sprintf("destination id %q does not match %q", destinationDestinationID, currentDestinationID),
Detail: ComparisonDetail{
Kind: ComparisonDetailDestinationIDMismatch,
CurrentDestinationID: currentDestinationID,
DestinationDestinationID: destinationDestinationID,
},
}
}
func manifestsEqual(a, b bundle.Manifest) bool {
if a.SchemaVersion != b.SchemaVersion ||
a.ID != b.ID ||

View File

@@ -97,6 +97,93 @@ func TestCompareOutcomes(t *testing.T) {
}
}
func TestCompareReportsStructuredDetails(t *testing.T) {
source := validManifest(t)
tests := []struct {
name string
status DestinationStatus
wantKind ComparisonDetailKind
assertions func(t *testing.T, detail ComparisonDetail)
}{
{
name: "pipeline mismatch",
status: DestinationStatus{State: withState(t, source, func(s *DistributorState) { s.PipelineID = "other" })},
wantKind: ComparisonDetailPipelineIDMismatch,
assertions: func(t *testing.T, detail ComparisonDetail) {
t.Helper()
if detail.DestinationPipelineID != "other" || detail.CurrentPipelineID != "reports" {
t.Fatalf("detail = %#v, want pipeline ids", detail)
}
},
},
{
name: "destination mismatch",
status: DestinationStatus{State: withState(t, source, func(s *DistributorState) { s.DestinationID = "other" })},
wantKind: ComparisonDetailDestinationIDMismatch,
assertions: func(t *testing.T, detail ComparisonDetail) {
t.Helper()
if detail.DestinationDestinationID != "other" || detail.CurrentDestinationID != "archive" {
t.Fatalf("detail = %#v, want destination ids", detail)
}
},
},
{
name: "different source id",
status: DestinationStatus{State: withState(t, source, func(s *DistributorState) { s.Source.Manifest.ID = "other.source" })},
wantKind: ComparisonDetailDifferentSourceID,
assertions: func(t *testing.T, detail ComparisonDetail) {
t.Helper()
if detail.DestinationSourceID != "other.source" || detail.CurrentSourceID != source.ID {
t.Fatalf("detail = %#v, want source ids", detail)
}
},
},
{
name: "same created digest conflict",
status: DestinationStatus{State: withState(t, source, func(s *DistributorState) {
s.Source.Manifest.Files[0].SHA256 = "sha256:3333333333333333333333333333333333333333333333333333333333333333"
s.Source.Manifest.Digest = bundle.BundleDigest(s.Source.Manifest.Files)
})},
wantKind: ComparisonDetailSameCreatedDigestConflict,
assertions: func(t *testing.T, detail ComparisonDetail) {
t.Helper()
if detail.CurrentSourceDigest == "" || detail.DestinationSourceDigest == "" || detail.CurrentSourceDigest == detail.DestinationSourceDigest {
t.Fatalf("detail = %#v, want different source digests", detail)
}
},
},
{
name: "destination newer",
status: DestinationStatus{State: withState(t, source, func(s *DistributorState) {
s.Source.Manifest.Created = source.Created.Add(time.Hour)
})},
wantKind: ComparisonDetailDestinationNewer,
},
{
name: "invalid state",
status: DestinationStatus{StateErr: errors.New("invalid json")},
wantKind: ComparisonDetailInvalidState,
},
{
name: "unmanaged content",
status: DestinationStatus{HasContents: true},
wantKind: ComparisonDetailUnmanagedContent,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
got := Compare(source, "reports", "archive", tt.status)
if got.Detail.Kind != tt.wantKind {
t.Fatalf("Compare() detail kind = %q, want %q; comparison=%#v", got.Detail.Kind, tt.wantKind, got)
}
if tt.assertions != nil {
tt.assertions(t, got.Detail)
}
})
}
}
func withState(t *testing.T, source bundle.Manifest, mutate func(*DistributorState)) *DistributorState {
t.Helper()
stateManifest := source

View File

@@ -14,9 +14,11 @@ import (
const (
SchemaVersion = 2
SharedRootSchemaVersion = 3
CatalogSchemaVersion = 4
legacySchemaVersion = 1
StateModeSingleOwner = config.StateModeSingleOwner
StateModeSharedRoot = config.StateModeSharedRoot
StateModeCatalog = "catalog"
)
type DistributorState struct {

View File

@@ -26,6 +26,15 @@ func FindOutputByPath(outputs []OutputFile, path string) (OutputFile, bool) {
return OutputFile{}, false
}
func FindCatalogOutputByPath(outputs []CatalogOutputFile, path string) (CatalogOutputFile, bool) {
for _, output := range outputs {
if output.Path == path {
return output, true
}
}
return CatalogOutputFile{}, false
}
func MergeOutputFiles(retained, planned []OutputFile) ([]OutputFile, error) {
outputs := make([]OutputFile, 0, len(retained)+len(planned))
indexByPath := make(map[string]int, len(retained)+len(planned))
@@ -178,6 +187,62 @@ func RemoveMissingSharedRootOutputs(s SharedRootState, missingPaths []string) (S
return next, changed
}
func CatalogOutputsForOwner(outputs []CatalogOutputFile, scope OwnerScope) []CatalogOutputFile {
selected := make([]CatalogOutputFile, 0, len(outputs))
for _, output := range outputs {
if output.PipelineID == scope.PipelineID && output.DestinationID == scope.DestinationID {
selected = append(selected, output)
}
}
return selected
}
func CatalogManagedOutputPaths(s CatalogState) []string {
paths := make([]string, 0, len(s.Outputs))
for _, output := range s.Outputs {
paths = append(paths, output.Path)
}
return paths
}
func RemoveMissingCatalogOwnerOutputs(s CatalogState, scope OwnerScope, missingPaths []string) (CatalogState, bool) {
if len(missingPaths) == 0 {
return s, false
}
missing := pathSet(missingPaths)
next := s
next.Outputs = make([]CatalogOutputFile, 0, len(s.Outputs))
changed := false
for _, output := range s.Outputs {
if output.PipelineID == scope.PipelineID && output.DestinationID == scope.DestinationID {
if _, remove := missing[output.Path]; remove {
changed = true
continue
}
}
next.Outputs = append(next.Outputs, output)
}
return next, changed
}
func RemoveMissingCatalogOutputs(s CatalogState, missingPaths []string) (CatalogState, bool) {
if len(missingPaths) == 0 {
return s, false
}
missing := pathSet(missingPaths)
next := s
next.Outputs = make([]CatalogOutputFile, 0, len(s.Outputs))
changed := false
for _, output := range s.Outputs {
if _, remove := missing[output.Path]; remove {
changed = true
continue
}
next.Outputs = append(next.Outputs, output)
}
return next, changed
}
func (s SharedRootState) OutputOwner(path string) (OwnerScope, bool) {
for _, output := range s.Outputs {
if output.Path == path {
@@ -191,7 +256,17 @@ func (s SharedRootState) PathOwnershipConflict(scope OwnerScope, paths []string)
for _, path := range paths {
owner, exists := s.OutputOwner(path)
if exists && owner != scope {
return PathOwnershipConflict{Path: path, Owner: owner}, true
return PathOwnershipConflict{
Path: path,
Owner: owner,
CurrentOwner: scope,
Detail: ComparisonDetail{
Kind: ComparisonDetailSharedRootOutputOwner,
Path: path,
CurrentOwner: scope,
ConflictingOwner: owner,
},
}, true
}
}
return PathOwnershipConflict{}, false

View File

@@ -49,6 +49,22 @@ func SharedRootPruneCandidates(s SharedRootState, scope OwnerScope) []PruneCandi
return candidates
}
func CatalogPruneCandidates(s CatalogState, scope OwnerScope) []PruneCandidate {
candidates := make([]PruneCandidate, 0, len(s.Outputs))
for _, output := range s.Outputs {
if output.PipelineID != scope.PipelineID || output.DestinationID != scope.DestinationID {
continue
}
owner := scope
candidates = append(candidates, PruneCandidate{
Path: output.Path,
UpdatedAt: output.UpdatedAt,
Owner: &owner,
})
}
return candidates
}
func PlanPrune(candidates []PruneCandidate, options PrunePlanOptions) PrunePlan {
ordered := append([]PruneCandidate(nil), candidates...)
sortPruneCandidatesNewestFirst(ordered)

View File

@@ -16,6 +16,12 @@ import (
type StateDocument struct {
SingleOwner *DistributorState
SharedRoot *SharedRootState
Catalog *CatalogState
SupersededLegacy *SupersededLegacyState
}
type SupersededLegacyState struct {
SchemaVersion int
}
type SharedRootState struct {
@@ -59,6 +65,8 @@ type SharedRootOutputFile struct {
type PathOwnershipConflict struct {
Path string
Owner OwnerScope
CurrentOwner OwnerScope
Detail ComparisonDetail
}
type rawSharedRootState struct {
@@ -101,18 +109,18 @@ func ParseDocument(data []byte) (StateDocument, error) {
if err != nil {
return StateDocument{}, err
}
if schemaVersion == SharedRootSchemaVersion {
sharedRoot, err := ParseSharedRoot(data)
switch schemaVersion {
case legacySchemaVersion, SchemaVersion, SharedRootSchemaVersion:
return StateDocument{SupersededLegacy: &SupersededLegacyState{SchemaVersion: schemaVersion}}, nil
case CatalogSchemaVersion:
catalog, err := ParseCatalog(data)
if err != nil {
return StateDocument{}, err
}
return StateDocument{SharedRoot: &sharedRoot}, nil
return StateDocument{Catalog: &catalog}, nil
default:
return StateDocument{}, fmt.Errorf("state schema_version %d is unsupported", schemaVersion)
}
singleOwner, err := Parse(data)
if err != nil {
return StateDocument{}, err
}
return StateDocument{SingleOwner: &singleOwner}, nil
}
func parseSchemaVersion(data []byte) (int, error) {
@@ -123,6 +131,10 @@ func parseSchemaVersion(data []byte) (int, error) {
if err := decoder.Decode(&raw); err != nil {
return 0, fmt.Errorf("parse distributor state: %w", err)
}
var extra any
if err := decoder.Decode(&extra); err != io.EOF {
return 0, fmt.Errorf("parse distributor state: trailing data")
}
if raw.SchemaVersion == nil {
return 0, fmt.Errorf("state schema_version is required")
}

View File

@@ -10,24 +10,6 @@ import (
"gitea.maximumdirect.net/eric/distributor/internal/config"
)
func TestParseDocumentHandlesSingleOwnerAndSharedRoot(t *testing.T) {
singleOwner, err := ParseDocument([]byte(validStateJSON(t)))
if err != nil {
t.Fatalf("ParseDocument(single owner) error = %v", err)
}
if singleOwner.SingleOwner == nil || singleOwner.SharedRoot != nil {
t.Fatalf("single owner document = %#v", singleOwner)
}
sharedRoot, err := ParseDocument([]byte(validSharedRootStateJSON(t)))
if err != nil {
t.Fatalf("ParseDocument(shared root) error = %v", err)
}
if sharedRoot.SharedRoot == nil || sharedRoot.SingleOwner != nil {
t.Fatalf("shared root document = %#v", sharedRoot)
}
}
func TestParseSharedRootState(t *testing.T) {
state, err := ParseSharedRoot([]byte(validSharedRootStateJSON(t)))
if err != nil {
@@ -130,6 +112,12 @@ func TestSharedRootOutputHelpers(t *testing.T) {
if !ok || conflict.Owner != html {
t.Fatalf("conflict = %#v ok=%t, want html owner conflict", conflict, ok)
}
if conflict.Detail.Kind != ComparisonDetailSharedRootOutputOwner {
t.Fatalf("conflict detail kind = %q, want %q", conflict.Detail.Kind, ComparisonDetailSharedRootOutputOwner)
}
if conflict.Detail.Path != "report.html" || conflict.Detail.CurrentOwner != archive || conflict.Detail.ConflictingOwner != html {
t.Fatalf("conflict detail = %#v, want path and owners", conflict.Detail)
}
}
func TestRemoveMissingSharedRootOwnerOutputs(t *testing.T) {
@@ -241,6 +229,12 @@ func TestCompareSharedRootOwnerScopesCurrentOwner(t *testing.T) {
if missing.Outcome != OutcomeDestinationAbsent {
t.Fatalf("missing owner comparison = %#v, want destination absent", missing)
}
if missing.Detail.Kind != ComparisonDetailSharedRootOwnerAbsent {
t.Fatalf("missing owner detail kind = %q, want %q", missing.Detail.Kind, ComparisonDetailSharedRootOwnerAbsent)
}
if missing.Detail.CurrentOwner != CurrentOwnerScope("missing", "archive") {
t.Fatalf("missing owner detail = %#v, want missing/archive", missing.Detail)
}
}
func TestCompareSharedRootOwnerAcceptsMatchingSingleOwnerState(t *testing.T) {

View File

@@ -123,7 +123,7 @@ func (t *Transformer) render(ctx context.Context, req transform.Request, sourceF
if err := t.renderer.Convert(data, &rendered); err != nil {
return nil, fmt.Errorf("render markdown source %q: %w", sourceFile, err)
}
return wrapHTML(rendered.Bytes()), nil
return wrapHTML(rendered.Bytes(), req.Markdown.CssHref), nil
}
func markdownMode(mode string) string {

View File

@@ -40,6 +40,43 @@ func TestGenerateMarkdownSidecar(t *testing.T) {
}
}
func TestGenerateMarkdownWithoutCSSHrefPreservesWrapper(t *testing.T) {
backend, sourceBundle := markdownFixture(t, "# Title\n\nHello.\n")
outputs, err := New().Generate(context.Background(), transform.Request{SourceBackend: backend, SourceBundle: sourceBundle})
if err != nil {
t.Fatalf("Generate() error = %v", err)
}
want := "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<title></title>\n</head>\n<body>\n<h1>Title</h1>\n<p>Hello.</p>\n</body>\n</html>\n"
if got := string(outputs[0].Data); got != want {
t.Fatalf("html = %q, want existing wrapper %q", got, want)
}
}
func TestGenerateMarkdownSidecarWithCSSHref(t *testing.T) {
backend, sourceBundle := markdownFixture(t, "# Title\n\nHello.\n")
outputs, err := New().Generate(context.Background(), transform.Request{
SourceBackend: backend,
SourceBundle: sourceBundle,
Markdown: transform.MarkdownOptions{CssHref: "/assets/report.css?v=1&theme=main"},
})
if err != nil {
t.Fatalf("Generate() error = %v", err)
}
output := outputs[0]
html := string(output.Data)
wantLink := "<meta charset=\"utf-8\">\n<link rel=\"stylesheet\" href=\"/assets/report.css?v=1&amp;theme=main\">\n<title></title>"
if !strings.Contains(html, wantLink) {
t.Fatalf("html = %q, want stylesheet link %q", html, wantLink)
}
if output.SHA256 != bundle.FileDigest(output.Data) || output.Size != int64(len(output.Data)) {
t.Fatalf("digest/size metadata = %s/%d", output.SHA256, output.Size)
}
}
func TestGenerateMarkdownIndexExplicitInput(t *testing.T) {
backend := fake.New()
sourceBundle := testutil.WriteFakeSourceBundle(t, backend, "", testutil.BundleOptions{
@@ -74,6 +111,29 @@ func TestGenerateMarkdownIndexExplicitInput(t *testing.T) {
}
}
func TestGenerateMarkdownIndexWithCSSHref(t *testing.T) {
backend, sourceBundle := markdownFixture(t, "# Title\n\nHello.\n")
outputs, err := New().Generate(context.Background(), transform.Request{
SourceBackend: backend,
SourceBundle: sourceBundle,
Markdown: transform.MarkdownOptions{
Mode: transform.MarkdownModeIndex,
CssHref: "https://example.com/assets/report.css",
},
})
if err != nil {
t.Fatalf("Generate() error = %v", err)
}
if got, want := outputs[0].Path, "index.html"; got != want {
t.Fatalf("path = %q, want %q", got, want)
}
if !strings.Contains(string(outputs[0].Data), `<link rel="stylesheet" href="https://example.com/assets/report.css">`) {
t.Fatalf("html = %q, want stylesheet link", outputs[0].Data)
}
}
func TestGenerateMarkdownIndexSelectsOnlyMarkdownFile(t *testing.T) {
backend, sourceBundle := markdownFixture(t, "# Title\n\nHello.\n")

View File

@@ -1,10 +1,19 @@
package markdown
import "bytes"
import (
"bytes"
"html"
)
func wrapHTML(body []byte) []byte {
func wrapHTML(body []byte, cssHref string) []byte {
var buf bytes.Buffer
buf.WriteString("<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<title></title>\n</head>\n<body>\n")
buf.WriteString("<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n")
if cssHref != "" {
buf.WriteString("<link rel=\"stylesheet\" href=\"")
buf.WriteString(html.EscapeString(cssHref))
buf.WriteString("\">\n")
}
buf.WriteString("<title></title>\n</head>\n<body>\n")
buf.Write(body)
buf.WriteString("</body>\n</html>\n")
return buf.Bytes()

View File

@@ -25,6 +25,7 @@ type Request struct {
type MarkdownOptions struct {
Mode string
Input string
CssHref string
}
type Transformer interface {