Add integration docs and synthetic command examples

examples/README.md

@@ -0,0 +1,61 @@
+# Examples
+
+These are small synthetic, copyable example assets for the implemented CLI
+commands.
+This directory is the canonical examples home for documentation.
+
+## Merge example
+
+Inputs:
+
+- `minimal-merge/input-alice.json`
+- `minimal-merge/input-bob.json`
+- `minimal-merge/speakers.yml`
+
+Run:
+
+```sh
+go run ./cmd/seriatim merge \
+  --input-file examples/minimal-merge/input-alice.json \
+  --input-file examples/minimal-merge/input-bob.json \
+  --speakers examples/minimal-merge/speakers.yml \
+  --output-file /tmp/seriatim-example-merge.json
+```
+
+## Normalize examples
+
+Object-with-segments input:
+
+```sh
+go run ./cmd/seriatim normalize \
+  --input-file examples/normalize/object-with-segments.json \
+  --output-file /tmp/seriatim-example-normalize-object.json
+```
+
+Bare-array input:
+
+```sh
+go run ./cmd/seriatim normalize \
+  --input-file examples/normalize/bare-segments-array.json \
+  --output-file /tmp/seriatim-example-normalize-array.json
+```
+
+## Trim example
+
+Input artifact:
+
+- `trim/input-full.json`
+
+Run:
+
+```sh
+go run ./cmd/seriatim trim \
+  --input-file examples/trim/input-full.json \
+  --output-file /tmp/seriatim-example-trim.json \
+  --keep "1-2"
+```
+
+## YAML rule examples
+
+- `speakers.yml`
+- `autocorrect.yml`

examples/autocorrect.yml

@@ -0,0 +1,8 @@
+autocorrect:
+  - target: "General Kenobi"
+    match:
+      - "General Kenobi."
+
+  - target: "Okay"
+    match:
+      - "Okay."

examples/minimal-merge/input-alice.json

@@ -0,0 +1,14 @@
+{
+  "segments": [
+    {
+      "start": 0.0,
+      "end": 1.2,
+      "text": " Hello there. "
+    },
+    {
+      "start": 2.6,
+      "end": 3.1,
+      "text": "Okay."
+    }
+  ]
+}

examples/minimal-merge/input-bob.json

@@ -0,0 +1,9 @@
+{
+  "segments": [
+    {
+      "start": 1.3,
+      "end": 2.4,
+      "text": "General Kenobi."
+    }
+  ]
+}

examples/minimal-merge/speakers.yml

@@ -0,0 +1,8 @@
+match:
+  - speaker: "Alice Example"
+    match:
+      - "alice"
+
+  - speaker: "Bob Example"
+    match:
+      - "bob"

examples/normalize/bare-segments-array.json

@@ -0,0 +1,13 @@
+[
+  {
+    "start": 2.5,
+    "end": 3.0,
+    "speaker": "Bob",
+    "text": "later"
+  },
+  {
+    "end": 2.0,
+    "speaker": "",
+    "text": "no start uses end"
+  }
+]

examples/normalize/object-with-segments.json

@@ -0,0 +1,19 @@
+{
+  "segments": [
+    {
+      "id": 7,
+      "start": 2.0,
+      "end": 2.5,
+      "speaker": "Bob",
+      "text": "second"
+    },
+    {
+      "id": 1,
+      "start": 1.0,
+      "end": 1.3,
+      "speaker": "Alice",
+      "text": "first",
+      "categories": ["backchannel"]
+    }
+  ]
+}

examples/speakers.yml

@@ -0,0 +1,8 @@
+match:
+  - speaker: "Alice Example"
+    match:
+      - "alice"
+
+  - speaker: "Bob Example"
+    match:
+      - "bob"

examples/trim/input-full.json

@@ -0,0 +1,64 @@
+{
+  "metadata": {
+    "application": "seriatim",
+    "version": "dev",
+    "input_reader": "json-files",
+    "input_files": [
+      "examples/minimal-merge/input-alice.json",
+      "examples/minimal-merge/input-bob.json"
+    ],
+    "preprocessing_modules": [
+      "validate-raw",
+      "normalize-speakers",
+      "trim-text"
+    ],
+    "postprocessing_modules": [
+      "detect-overlaps",
+      "resolve-overlaps",
+      "backchannel",
+      "filler",
+      "resolve-danglers",
+      "coalesce",
+      "detect-overlaps",
+      "autocorrect",
+      "assign-ids",
+      "validate-output"
+    ],
+    "output_modules": [
+      "json"
+    ]
+  },
+  "segments": [
+    {
+      "id": 1,
+      "source": "examples/minimal-merge/input-alice.json",
+      "source_segment_index": 0,
+      "speaker": "Alice Example",
+      "start": 0,
+      "end": 1.2,
+      "text": "Hello there."
+    },
+    {
+      "id": 2,
+      "source": "examples/minimal-merge/input-bob.json",
+      "source_segment_index": 0,
+      "speaker": "Bob Example",
+      "start": 1.3,
+      "end": 2.4,
+      "text": "General Kenobi."
+    },
+    {
+      "id": 3,
+      "source": "examples/minimal-merge/input-alice.json",
+      "source_segment_index": 1,
+      "speaker": "Alice Example",
+      "start": 2.6,
+      "end": 3.1,
+      "text": "Okay.",
+      "categories": [
+        "backchannel"
+      ]
+    }
+  ],
+  "overlap_groups": []
+}