47df769e4b
Implement the --json output sink for pdftract grep with JSON-Lines format (one match per line). Includes MatchEvent, FileOnlyEvent, CountEvent structs and JsonSink line-buffered writer. Key features: - MatchEvent with all fields (path, page_index, bbox, match_text, span_text, span_confidence, pdf_fingerprint, crosses_spans) - crosses_spans omitted when false via skip_serializing_if - NaN/Infinity in span_confidence replaced with null - page_index is 0-based (machine convention) - FileOnlyEvent for -l mode, CountEvent for -c mode - Line-buffered writes with immediate flush - JSON schema at docs/schema/v1.0/grep-jsonl.schema.json Closes: pdftract-5ls35
97 lines
3 KiB
JSON
97 lines
3 KiB
JSON
{
|
|
"$schema": "http://json-schema.org/draft-07/schema#",
|
|
"$id": "https://pdftract.jedarden.com/schemas/v1.0/grep-jsonl.schema.json",
|
|
"title": "pdftract grep JSON-Lines output",
|
|
"description": "One match per line in JSON format. Each line is a separate JSON object with match metadata.",
|
|
"type": "object",
|
|
"anyOf": [
|
|
{
|
|
"$ref": "#/definitions/MatchEvent"
|
|
},
|
|
{
|
|
"$ref": "#/definitions/FileOnlyEvent"
|
|
},
|
|
{
|
|
"$ref": "#/definitions/CountEvent"
|
|
}
|
|
],
|
|
"definitions": {
|
|
"MatchEvent": {
|
|
"description": "A single grep match with full metadata (default output mode)",
|
|
"type": "object",
|
|
"required": ["path", "page_index", "bbox", "match_text", "span_text", "pdf_fingerprint"],
|
|
"properties": {
|
|
"path": {
|
|
"type": "string",
|
|
"description": "Path to the PDF file (relative if input was relative, absolute if input was absolute)"
|
|
},
|
|
"page_index": {
|
|
"type": "integer",
|
|
"minimum": 0,
|
|
"description": "0-based page index (machine convention; human output flips to 1-based)"
|
|
},
|
|
"bbox": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "number"
|
|
},
|
|
"minItems": 4,
|
|
"maxItems": 4,
|
|
"description": "Bounding box in PDF user-space coordinates [x0, y0, x1, y1]"
|
|
},
|
|
"match_text": {
|
|
"type": "string",
|
|
"description": "The matched text substring"
|
|
},
|
|
"span_text": {
|
|
"type": "string",
|
|
"description": "The full span text containing the match"
|
|
},
|
|
"span_confidence": {
|
|
"type": "number",
|
|
"minimum": 0.0,
|
|
"maximum": 1.0,
|
|
"description": "Confidence score (0.0 to 1.0). Omitted (null) if not applicable (e.g., non-OCR text or NaN/Infinity values)."
|
|
},
|
|
"pdf_fingerprint": {
|
|
"type": "string",
|
|
"pattern": "^pdftract-v1:[0-9a-f]{64}$",
|
|
"description": "PDF structural fingerprint for deduplication across runs"
|
|
},
|
|
"crosses_spans": {
|
|
"type": "boolean",
|
|
"description": "Whether the match crosses multiple spans. Omitted when false to keep typical lines short."
|
|
}
|
|
}
|
|
},
|
|
"FileOnlyEvent": {
|
|
"description": "File-only event emitted with -l (files-with-matches) flag",
|
|
"type": "object",
|
|
"required": ["path"],
|
|
"properties": {
|
|
"path": {
|
|
"type": "string",
|
|
"description": "Path to the PDF file with at least one match"
|
|
}
|
|
},
|
|
"additionalProperties": false
|
|
},
|
|
"CountEvent": {
|
|
"description": "Count event emitted with -c (count) flag",
|
|
"type": "object",
|
|
"required": ["path", "count"],
|
|
"properties": {
|
|
"path": {
|
|
"type": "string",
|
|
"description": "Path to the PDF file"
|
|
},
|
|
"count": {
|
|
"type": "integer",
|
|
"minimum": 0,
|
|
"description": "Number of matches in this file"
|
|
}
|
|
},
|
|
"additionalProperties": false
|
|
}
|
|
}
|
|
}
|