@usejunior/docx-core 0.2.0 → 0.3.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +0 -2
- package/dist/.tsbuildinfo +1 -1
- package/dist/atomizer.d.ts.map +1 -1
- package/dist/atomizer.js +16 -3
- package/dist/atomizer.js.map +1 -1
- package/dist/baselines/atomizer/documentReconstructor.d.ts.map +1 -1
- package/dist/baselines/atomizer/documentReconstructor.js +11 -5
- package/dist/baselines/atomizer/documentReconstructor.js.map +1 -1
- package/dist/baselines/atomizer/inPlaceModifier.d.ts +81 -1
- package/dist/baselines/atomizer/inPlaceModifier.d.ts.map +1 -1
- package/dist/baselines/atomizer/inPlaceModifier.js +618 -34
- package/dist/baselines/atomizer/inPlaceModifier.js.map +1 -1
- package/dist/baselines/atomizer/pipeline.d.ts +1 -1
- package/dist/baselines/atomizer/pipeline.d.ts.map +1 -1
- package/dist/baselines/atomizer/pipeline.js +70 -1
- package/dist/baselines/atomizer/pipeline.js.map +1 -1
- package/dist/baselines/atomizer/premergeRuns.d.ts.map +1 -1
- package/dist/baselines/atomizer/premergeRuns.js +3 -0
- package/dist/baselines/atomizer/premergeRuns.js.map +1 -1
- package/dist/baselines/atomizer/trackChangesAcceptorAst.d.ts.map +1 -1
- package/dist/baselines/atomizer/trackChangesAcceptorAst.js +63 -33
- package/dist/baselines/atomizer/trackChangesAcceptorAst.js.map +1 -1
- package/dist/cli/compare-two.js +4 -4
- package/dist/cli/compare-two.js.map +1 -1
- package/dist/index.d.ts +6 -6
- package/dist/index.d.ts.map +1 -1
- package/dist/index.js +7 -7
- package/dist/index.js.map +1 -1
- package/dist/primitives/document.d.ts +12 -0
- package/dist/primitives/document.d.ts.map +1 -1
- package/dist/primitives/document.js +17 -2
- package/dist/primitives/document.js.map +1 -1
- package/dist/primitives/document_view.d.ts +2 -0
- package/dist/primitives/document_view.d.ts.map +1 -1
- package/dist/primitives/document_view.js +3 -2
- package/dist/primitives/document_view.js.map +1 -1
- package/dist/primitives/formatting_tags.d.ts +14 -2
- package/dist/primitives/formatting_tags.d.ts.map +1 -1
- package/dist/primitives/formatting_tags.js +13 -11
- package/dist/primitives/formatting_tags.js.map +1 -1
- package/dist/primitives/matching.d.ts +12 -0
- package/dist/primitives/matching.d.ts.map +1 -1
- package/dist/primitives/matching.js +54 -0
- package/dist/primitives/matching.js.map +1 -1
- package/dist/primitives/merge_runs.d.ts.map +1 -1
- package/dist/primitives/merge_runs.js +48 -0
- package/dist/primitives/merge_runs.js.map +1 -1
- package/dist/shared/validators/structural.d.ts +31 -0
- package/dist/shared/validators/structural.d.ts.map +1 -0
- package/dist/shared/validators/structural.js +110 -0
- package/dist/shared/validators/structural.js.map +1 -0
- package/package.json +2 -2
- package/dist/baselines/diffmatch/documentBuilder.d.ts +0 -44
- package/dist/baselines/diffmatch/documentBuilder.d.ts.map +0 -1
- package/dist/baselines/diffmatch/documentBuilder.js +0 -227
- package/dist/baselines/diffmatch/documentBuilder.js.map +0 -1
- package/dist/baselines/diffmatch/paragraphAlignment.d.ts +0 -75
- package/dist/baselines/diffmatch/paragraphAlignment.d.ts.map +0 -1
- package/dist/baselines/diffmatch/paragraphAlignment.js +0 -206
- package/dist/baselines/diffmatch/paragraphAlignment.js.map +0 -1
- package/dist/baselines/diffmatch/pipeline.d.ts +0 -33
- package/dist/baselines/diffmatch/pipeline.d.ts.map +0 -1
- package/dist/baselines/diffmatch/pipeline.js +0 -84
- package/dist/baselines/diffmatch/pipeline.js.map +0 -1
- package/dist/baselines/diffmatch/runDiff.d.ts +0 -53
- package/dist/baselines/diffmatch/runDiff.d.ts.map +0 -1
- package/dist/baselines/diffmatch/runDiff.js +0 -253
- package/dist/baselines/diffmatch/runDiff.js.map +0 -1
- package/dist/baselines/diffmatch/trackChangesRenderer.d.ts +0 -64
- package/dist/baselines/diffmatch/trackChangesRenderer.d.ts.map +0 -1
- package/dist/baselines/diffmatch/trackChangesRenderer.js +0 -178
- package/dist/baselines/diffmatch/trackChangesRenderer.js.map +0 -1
- package/dist/baselines/diffmatch/xmlParser.d.ts +0 -45
- package/dist/baselines/diffmatch/xmlParser.d.ts.map +0 -1
- package/dist/baselines/diffmatch/xmlParser.js +0 -216
- package/dist/baselines/diffmatch/xmlParser.js.map +0 -1
- package/dist/benchmark/metrics.d.ts +0 -72
- package/dist/benchmark/metrics.d.ts.map +0 -1
- package/dist/benchmark/metrics.js +0 -45
- package/dist/benchmark/metrics.js.map +0 -1
- package/dist/benchmark/reporter.d.ts +0 -23
- package/dist/benchmark/reporter.d.ts.map +0 -1
- package/dist/benchmark/reporter.js +0 -147
- package/dist/benchmark/reporter.js.map +0 -1
- package/dist/benchmark/runner.d.ts +0 -30
- package/dist/benchmark/runner.d.ts.map +0 -1
- package/dist/benchmark/runner.js +0 -233
- package/dist/benchmark/runner.js.map +0 -1
|
@@ -0,0 +1,110 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* Structural OOXML validators.
|
|
3
|
+
*
|
|
4
|
+
* General-purpose integrity checks for numbering, footnotes/endnotes,
|
|
5
|
+
* and bookmarks. Used by both integration tests and the quality benchmark.
|
|
6
|
+
*/
|
|
7
|
+
import { parseXml } from '../../primitives/xml.js';
|
|
8
|
+
import { findAllByTagName, childElements } from '../../primitives/dom-helpers.js';
|
|
9
|
+
// ── Helpers ─────────────────────────────────────────────────────────
|
|
10
|
+
export function collectIds(root, tagName, attributeName) {
|
|
11
|
+
const values = new Set();
|
|
12
|
+
const duplicateValues = new Set();
|
|
13
|
+
for (const node of findAllByTagName(root, tagName)) {
|
|
14
|
+
const value = node.getAttribute(attributeName);
|
|
15
|
+
if (!value) {
|
|
16
|
+
continue;
|
|
17
|
+
}
|
|
18
|
+
if (values.has(value)) {
|
|
19
|
+
duplicateValues.add(value);
|
|
20
|
+
}
|
|
21
|
+
else {
|
|
22
|
+
values.add(value);
|
|
23
|
+
}
|
|
24
|
+
}
|
|
25
|
+
return { values, duplicates: Array.from(duplicateValues).sort() };
|
|
26
|
+
}
|
|
27
|
+
// ── Validators ──────────────────────────────────────────────────────
|
|
28
|
+
export function validateNumberingIntegrity(documentXml, numberingXml) {
|
|
29
|
+
const documentRoot = parseXml(documentXml).documentElement;
|
|
30
|
+
const numRefIds = collectIds(documentRoot, 'w:numId', 'w:val').values;
|
|
31
|
+
const ilvlNodes = findAllByTagName(documentRoot, 'w:ilvl');
|
|
32
|
+
const invalidLevels = [];
|
|
33
|
+
for (const node of ilvlNodes) {
|
|
34
|
+
const rawLevel = node.getAttribute('w:val');
|
|
35
|
+
if (!rawLevel) {
|
|
36
|
+
continue;
|
|
37
|
+
}
|
|
38
|
+
const parsed = Number.parseInt(rawLevel, 10);
|
|
39
|
+
if (!Number.isFinite(parsed) || parsed < 0 || parsed > 8) {
|
|
40
|
+
invalidLevels.push(rawLevel);
|
|
41
|
+
}
|
|
42
|
+
}
|
|
43
|
+
if (!numberingXml) {
|
|
44
|
+
return {
|
|
45
|
+
missingNumIds: Array.from(numRefIds).sort(),
|
|
46
|
+
missingAbstractNumIds: [],
|
|
47
|
+
invalidLevels: invalidLevels.sort(),
|
|
48
|
+
};
|
|
49
|
+
}
|
|
50
|
+
const numberingRoot = parseXml(numberingXml).documentElement;
|
|
51
|
+
const numDefinitions = collectIds(numberingRoot, 'w:num', 'w:numId').values;
|
|
52
|
+
const abstractDefinitions = collectIds(numberingRoot, 'w:abstractNum', 'w:abstractNumId').values;
|
|
53
|
+
const abstractRefs = new Set();
|
|
54
|
+
for (const numNode of findAllByTagName(numberingRoot, 'w:num')) {
|
|
55
|
+
const abstractNode = childElements(numNode).find((child) => child.tagName === 'w:abstractNumId');
|
|
56
|
+
const abstractId = abstractNode?.getAttribute('w:val');
|
|
57
|
+
if (abstractId) {
|
|
58
|
+
abstractRefs.add(abstractId);
|
|
59
|
+
}
|
|
60
|
+
}
|
|
61
|
+
// In WordprocessingML, numId="0" is a sentinel that means "no numbering".
|
|
62
|
+
const missingNumIds = Array.from(numRefIds)
|
|
63
|
+
.filter((id) => id !== '0' && !numDefinitions.has(id))
|
|
64
|
+
.sort();
|
|
65
|
+
const missingAbstractNumIds = Array.from(abstractRefs)
|
|
66
|
+
.filter((id) => !abstractDefinitions.has(id))
|
|
67
|
+
.sort();
|
|
68
|
+
return {
|
|
69
|
+
missingNumIds,
|
|
70
|
+
missingAbstractNumIds,
|
|
71
|
+
invalidLevels: invalidLevels.sort(),
|
|
72
|
+
};
|
|
73
|
+
}
|
|
74
|
+
export function validateNoteIntegrity(documentXml, footnotesXml, endnotesXml) {
|
|
75
|
+
const documentRoot = parseXml(documentXml).documentElement;
|
|
76
|
+
const footnoteRefs = collectIds(documentRoot, 'w:footnoteReference', 'w:id').values;
|
|
77
|
+
const endnoteRefs = collectIds(documentRoot, 'w:endnoteReference', 'w:id').values;
|
|
78
|
+
const footnoteIds = footnotesXml
|
|
79
|
+
? collectIds(parseXml(footnotesXml).documentElement, 'w:footnote', 'w:id')
|
|
80
|
+
: { values: new Set(), duplicates: [] };
|
|
81
|
+
const endnoteIds = endnotesXml
|
|
82
|
+
? collectIds(parseXml(endnotesXml).documentElement, 'w:endnote', 'w:id')
|
|
83
|
+
: { values: new Set(), duplicates: [] };
|
|
84
|
+
const missingFootnoteRefs = Array.from(footnoteRefs)
|
|
85
|
+
.filter((id) => !footnoteIds.values.has(id))
|
|
86
|
+
.sort();
|
|
87
|
+
const missingEndnoteRefs = Array.from(endnoteRefs)
|
|
88
|
+
.filter((id) => !endnoteIds.values.has(id))
|
|
89
|
+
.sort();
|
|
90
|
+
return {
|
|
91
|
+
missingFootnoteRefs,
|
|
92
|
+
missingEndnoteRefs,
|
|
93
|
+
duplicateFootnoteIds: footnoteIds.duplicates,
|
|
94
|
+
duplicateEndnoteIds: endnoteIds.duplicates,
|
|
95
|
+
};
|
|
96
|
+
}
|
|
97
|
+
export function validateBookmarkIntegrity(documentXml) {
|
|
98
|
+
const root = parseXml(documentXml).documentElement;
|
|
99
|
+
const starts = collectIds(root, 'w:bookmarkStart', 'w:id');
|
|
100
|
+
const ends = collectIds(root, 'w:bookmarkEnd', 'w:id');
|
|
101
|
+
const unmatchedStartIds = Array.from(starts.values).filter((id) => !ends.values.has(id)).sort();
|
|
102
|
+
const unmatchedEndIds = Array.from(ends.values).filter((id) => !starts.values.has(id)).sort();
|
|
103
|
+
return {
|
|
104
|
+
unmatchedStartIds,
|
|
105
|
+
unmatchedEndIds,
|
|
106
|
+
duplicateStartIds: starts.duplicates,
|
|
107
|
+
duplicateEndIds: ends.duplicates,
|
|
108
|
+
};
|
|
109
|
+
}
|
|
110
|
+
//# sourceMappingURL=structural.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"structural.js","sourceRoot":"","sources":["../../../src/shared/validators/structural.ts"],"names":[],"mappings":"AAAA;;;;;GAKG;AAEH,OAAO,EAAE,QAAQ,EAAE,MAAM,yBAAyB,CAAC;AACnD,OAAO,EAAE,gBAAgB,EAAE,aAAa,EAAE,MAAM,iCAAiC,CAAC;AAwBlF,uEAAuE;AAEvE,MAAM,UAAU,UAAU,CACxB,IAAa,EACb,OAAe,EACf,aAAqB;IAErB,MAAM,MAAM,GAAG,IAAI,GAAG,EAAU,CAAC;IACjC,MAAM,eAAe,GAAG,IAAI,GAAG,EAAU,CAAC;IAE1C,KAAK,MAAM,IAAI,IAAI,gBAAgB,CAAC,IAAI,EAAE,OAAO,CAAC,EAAE,CAAC;QACnD,MAAM,KAAK,GAAG,IAAI,CAAC,YAAY,CAAC,aAAa,CAAC,CAAC;QAC/C,IAAI,CAAC,KAAK,EAAE,CAAC;YACX,SAAS;QACX,CAAC;QACD,IAAI,MAAM,CAAC,GAAG,CAAC,KAAK,CAAC,EAAE,CAAC;YACtB,eAAe,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;QAC7B,CAAC;aAAM,CAAC;YACN,MAAM,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;QACpB,CAAC;IACH,CAAC;IAED,OAAO,EAAE,MAAM,EAAE,UAAU,EAAE,KAAK,CAAC,IAAI,CAAC,eAAe,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC;AACpE,CAAC;AAED,uEAAuE;AAEvE,MAAM,UAAU,0BAA0B,CACxC,WAAmB,EACnB,YAA2B;IAE3B,MAAM,YAAY,GAAG,QAAQ,CAAC,WAAW,CAAC,CAAC,eAAgB,CAAC;IAC5D,MAAM,SAAS,GAAG,UAAU,CAAC,YAAY,EAAE,SAAS,EAAE,OAAO,CAAC,CAAC,MAAM,CAAC;IACtE,MAAM,SAAS,GAAG,gBAAgB,CAAC,YAAY,EAAE,QAAQ,CAAC,CAAC;IAE3D,MAAM,aAAa,GAAa,EAAE,CAAC;IACnC,KAAK,MAAM,IAAI,IAAI,SAAS,EAAE,CAAC;QAC7B,MAAM,QAAQ,GAAG,IAAI,CAAC,YAAY,CAAC,OAAO,CAAC,CAAC;QAC5C,IAAI,CAAC,QAAQ,EAAE,CAAC;YACd,SAAS;QACX,CAAC;QACD,MAAM,MAAM,GAAG,MAAM,CAAC,QAAQ,CAAC,QAAQ,EAAE,EAAE,CAAC,CAAC;QAC7C,IAAI,CAAC,MAAM,CAAC,QAAQ,CAAC,MAAM,CAAC,IAAI,MAAM,GAAG,CAAC,IAAI,MAAM,GAAG,CAAC,EAAE,CAAC;YACzD,aAAa,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC;QAC/B,CAAC;IACH,CAAC;IAED,IAAI,CAAC,YAAY,EAAE,CAAC;QAClB,OAAO;YACL,aAAa,EAAE,KAAK,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC,IAAI,EAAE;YAC3C,qBAAqB,EAAE,EAAE;YACzB,aAAa,EAAE,aAAa,CAAC,IAAI,EAAE;SACpC,CAAC;IACJ,CAAC;IAED,MAAM,aAAa,GAAG,QAAQ,CAAC,YAAY,CAAC,CAAC,eAAgB,CAAC;IAC9D,MAAM,cAAc,GAAG,UAAU,CAAC,aAAa,EAAE,OAAO,EAAE,SAAS,CAAC,CAAC,MAAM,CAAC;IAC5E,MAAM,mBAAmB,GAAG,UAAU,CAAC,aAAa,EAAE,eAAe,EAAE,iBAAiB,CAAC,CAAC,MAAM,CAAC;IAEjG,MAAM,YAAY,GAAG,IAAI,GAAG,EAAU,CAAC;IACvC,KAAK,MAAM,OAAO,IAAI,gBAAgB,CAAC,aAAa,EAAE,OAAO,CAAC,EAAE,CAAC;QAC/D,MAAM,YAAY,GAAG,aAAa,CAAC,OAAO,CAAC,CAAC,IAAI,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,OAAO,KAAK,iBAAiB,CAAC,CAAC;QACjG,MAAM,UAAU,GAAG,YAAY,EAAE,YAAY,CAAC,OAAO,CAAC,CAAC;QACvD,IAAI,UAAU,EAAE,CAAC;YACf,YAAY,CAAC,GAAG,CAAC,UAAU,CAAC,CAAC;QAC/B,CAAC;IACH,CAAC;IAED,0EAA0E;IAC1E,MAAM,aAAa,GAAG,KAAK,CAAC,IAAI,CAAC,SAAS,CAAC;SACxC,MAAM,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,EAAE,KAAK,GAAG,IAAI,CAAC,cAAc,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC;SACrD,IAAI,EAAE,CAAC;IACV,MAAM,qBAAqB,GAAG,KAAK,CAAC,IAAI,CAAC,YAAY,CAAC;SACnD,MAAM,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,mBAAmB,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC;SAC5C,IAAI,EAAE,CAAC;IAEV,OAAO;QACL,aAAa;QACb,qBAAqB;QACrB,aAAa,EAAE,aAAa,CAAC,IAAI,EAAE;KACpC,CAAC;AACJ,CAAC;AAED,MAAM,UAAU,qBAAqB,CACnC,WAAmB,EACnB,YAA2B,EAC3B,WAA0B;IAE1B,MAAM,YAAY,GAAG,QAAQ,CAAC,WAAW,CAAC,CAAC,eAAgB,CAAC;IAC5D,MAAM,YAAY,GAAG,UAAU,CAAC,YAAY,EAAE,qBAAqB,EAAE,MAAM,CAAC,CAAC,MAAM,CAAC;IACpF,MAAM,WAAW,GAAG,UAAU,CAAC,YAAY,EAAE,oBAAoB,EAAE,MAAM,CAAC,CAAC,MAAM,CAAC;IAElF,MAAM,WAAW,GAAG,YAAY;QAC9B,CAAC,CAAC,UAAU,CAAC,QAAQ,CAAC,YAAY,CAAC,CAAC,eAAgB,EAAE,YAAY,EAAE,MAAM,CAAC;QAC3E,CAAC,CAAC,EAAE,MAAM,EAAE,IAAI,GAAG,EAAU,EAAE,UAAU,EAAE,EAAc,EAAE,CAAC;IAC9D,MAAM,UAAU,GAAG,WAAW;QAC5B,CAAC,CAAC,UAAU,CAAC,QAAQ,CAAC,WAAW,CAAC,CAAC,eAAgB,EAAE,WAAW,EAAE,MAAM,CAAC;QACzE,CAAC,CAAC,EAAE,MAAM,EAAE,IAAI,GAAG,EAAU,EAAE,UAAU,EAAE,EAAc,EAAE,CAAC;IAE9D,MAAM,mBAAmB,GAAG,KAAK,CAAC,IAAI,CAAC,YAAY,CAAC;SACjD,MAAM,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,WAAW,CAAC,MAAM,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC;SAC3C,IAAI,EAAE,CAAC;IACV,MAAM,kBAAkB,GAAG,KAAK,CAAC,IAAI,CAAC,WAAW,CAAC;SAC/C,MAAM,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,UAAU,CAAC,MAAM,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC;SAC1C,IAAI,EAAE,CAAC;IAEV,OAAO;QACL,mBAAmB;QACnB,kBAAkB;QAClB,oBAAoB,EAAE,WAAW,CAAC,UAAU;QAC5C,mBAAmB,EAAE,UAAU,CAAC,UAAU;KAC3C,CAAC;AACJ,CAAC;AAED,MAAM,UAAU,yBAAyB,CAAC,WAAmB;IAC3D,MAAM,IAAI,GAAG,QAAQ,CAAC,WAAW,CAAC,CAAC,eAAgB,CAAC;IACpD,MAAM,MAAM,GAAG,UAAU,CAAC,IAAI,EAAE,iBAAiB,EAAE,MAAM,CAAC,CAAC;IAC3D,MAAM,IAAI,GAAG,UAAU,CAAC,IAAI,EAAE,eAAe,EAAE,MAAM,CAAC,CAAC;IAEvD,MAAM,iBAAiB,GAAG,KAAK,CAAC,IAAI,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,MAAM,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,IAAI,CAAC,MAAM,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC;IAChG,MAAM,eAAe,GAAG,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC,MAAM,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,MAAM,CAAC,MAAM,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC;IAE9F,OAAO;QACL,iBAAiB;QACjB,eAAe;QACf,iBAAiB,EAAE,MAAM,CAAC,UAAU;QACpC,eAAe,EAAE,IAAI,CAAC,UAAU;KACjC,CAAC;AACJ,CAAC"}
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@usejunior/docx-core",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "0.3.1",
|
|
4
4
|
"description": "OOXML (.docx) core library: primitives, comparison, and track changes",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"main": "dist/index.js",
|
|
@@ -20,10 +20,10 @@
|
|
|
20
20
|
},
|
|
21
21
|
"dependencies": {
|
|
22
22
|
"@xmldom/xmldom": "^0.8.10",
|
|
23
|
-
"diff-match-patch": "^1.0.5",
|
|
24
23
|
"jszip": "^3.10.1"
|
|
25
24
|
},
|
|
26
25
|
"devDependencies": {
|
|
26
|
+
"diff-match-patch": "^1.0.5",
|
|
27
27
|
"@types/diff-match-patch": "^1.0.36",
|
|
28
28
|
"@types/node": "^22.10.0",
|
|
29
29
|
"@vitest/coverage-v8": "^3.2.4",
|
|
@@ -1,44 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* Document builder for reconstructing DOCX with track changes.
|
|
3
|
-
*
|
|
4
|
-
* Takes alignment results and produces a new document.xml with
|
|
5
|
-
* insertions and deletions marked using OOXML track changes.
|
|
6
|
-
*/
|
|
7
|
-
import type { AlignmentResult } from '../../shared/ooxml/types.js';
|
|
8
|
-
import { type ExtendedParagraphInfo } from './xmlParser.js';
|
|
9
|
-
/**
|
|
10
|
-
* Build options for document generation.
|
|
11
|
-
*/
|
|
12
|
-
export interface BuildOptions {
|
|
13
|
-
author: string;
|
|
14
|
-
date: Date;
|
|
15
|
-
}
|
|
16
|
-
/**
|
|
17
|
-
* Represents a paragraph operation in the output document.
|
|
18
|
-
*/
|
|
19
|
-
export interface ParagraphOperation {
|
|
20
|
-
/** Type of operation */
|
|
21
|
-
type: 'unchanged' | 'modified' | 'deleted' | 'inserted';
|
|
22
|
-
/** Generated XML for this paragraph */
|
|
23
|
-
xml: string;
|
|
24
|
-
/** Index in original document (for ordering) */
|
|
25
|
-
originalIndex?: number;
|
|
26
|
-
/** Index in revised document (for ordering) */
|
|
27
|
-
revisedIndex?: number;
|
|
28
|
-
}
|
|
29
|
-
/**
|
|
30
|
-
* Generate paragraph operations from alignment result.
|
|
31
|
-
*
|
|
32
|
-
* This converts the alignment result into a list of XML paragraph operations
|
|
33
|
-
* that can be used to build the output document.
|
|
34
|
-
*/
|
|
35
|
-
export declare function generateParagraphOperations(alignment: AlignmentResult, originalParagraphs: ExtendedParagraphInfo[], revisedParagraphs: ExtendedParagraphInfo[], options: BuildOptions): ParagraphOperation[];
|
|
36
|
-
/**
|
|
37
|
-
* Build a new document.xml with track changes applied.
|
|
38
|
-
*
|
|
39
|
-
* @param originalXml - The original document.xml content
|
|
40
|
-
* @param operations - Ordered list of paragraph operations
|
|
41
|
-
* @returns The new document.xml content
|
|
42
|
-
*/
|
|
43
|
-
export declare function buildDocumentWithTrackChanges(originalXml: string, operations: ParagraphOperation[]): string;
|
|
44
|
-
//# sourceMappingURL=documentBuilder.d.ts.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"documentBuilder.d.ts","sourceRoot":"","sources":["../../../src/baselines/diffmatch/documentBuilder.ts"],"names":[],"mappings":"AAAA;;;;;GAKG;AAEH,OAAO,KAAK,EAAE,eAAe,EAAW,MAAM,6BAA6B,CAAC;AAQ5E,OAAO,EAAiB,KAAK,qBAAqB,EAAE,MAAM,gBAAgB,CAAC;AAE3E;;GAEG;AACH,MAAM,WAAW,YAAY;IAC3B,MAAM,EAAE,MAAM,CAAC;IACf,IAAI,EAAE,IAAI,CAAC;CACZ;AAED;;GAEG;AACH,MAAM,WAAW,kBAAkB;IACjC,wBAAwB;IACxB,IAAI,EAAE,WAAW,GAAG,UAAU,GAAG,SAAS,GAAG,UAAU,CAAC;IACxD,uCAAuC;IACvC,GAAG,EAAE,MAAM,CAAC;IACZ,gDAAgD;IAChD,aAAa,CAAC,EAAE,MAAM,CAAC;IACvB,+CAA+C;IAC/C,YAAY,CAAC,EAAE,MAAM,CAAC;CACvB;AAED;;;;;GAKG;AACH,wBAAgB,2BAA2B,CACzC,SAAS,EAAE,eAAe,EAC1B,kBAAkB,EAAE,qBAAqB,EAAE,EAC3C,iBAAiB,EAAE,qBAAqB,EAAE,EAC1C,OAAO,EAAE,YAAY,GACpB,kBAAkB,EAAE,CAkItB;AAED;;;;;;GAMG;AACH,wBAAgB,6BAA6B,CAC3C,WAAW,EAAE,MAAM,EACnB,UAAU,EAAE,kBAAkB,EAAE,GAC/B,MAAM,CAkBR"}
|
|
@@ -1,227 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* Document builder for reconstructing DOCX with track changes.
|
|
3
|
-
*
|
|
4
|
-
* Takes alignment results and produces a new document.xml with
|
|
5
|
-
* insertions and deletions marked using OOXML track changes.
|
|
6
|
-
*/
|
|
7
|
-
import { diffRuns } from './runDiff.js';
|
|
8
|
-
import { renderTrackChanges, generateDeletedParagraph, generateInsertedParagraph, wrapInParagraph, } from './trackChangesRenderer.js';
|
|
9
|
-
import { extractSectPr } from './xmlParser.js';
|
|
10
|
-
/**
|
|
11
|
-
* Generate paragraph operations from alignment result.
|
|
12
|
-
*
|
|
13
|
-
* This converts the alignment result into a list of XML paragraph operations
|
|
14
|
-
* that can be used to build the output document.
|
|
15
|
-
*/
|
|
16
|
-
export function generateParagraphOperations(alignment, originalParagraphs, revisedParagraphs, options) {
|
|
17
|
-
const operations = [];
|
|
18
|
-
const { author, date } = options;
|
|
19
|
-
// Build lookup maps for original paragraphs by index
|
|
20
|
-
const originalByIndex = new Map();
|
|
21
|
-
for (const p of originalParagraphs) {
|
|
22
|
-
originalByIndex.set(p.originalIndex, p);
|
|
23
|
-
}
|
|
24
|
-
// Build lookup maps for revised paragraphs by index
|
|
25
|
-
const revisedByIndex = new Map();
|
|
26
|
-
for (const p of revisedParagraphs) {
|
|
27
|
-
revisedByIndex.set(p.originalIndex, p);
|
|
28
|
-
}
|
|
29
|
-
// Track which original paragraphs have been matched
|
|
30
|
-
const matchedOriginalIndices = new Set();
|
|
31
|
-
const matchedRevisedIndices = new Set();
|
|
32
|
-
// Build a map from revised index to the matching original paragraph
|
|
33
|
-
const revisedToOriginal = new Map();
|
|
34
|
-
for (const match of alignment.matched) {
|
|
35
|
-
const origPara = match.original;
|
|
36
|
-
const revPara = match.revised;
|
|
37
|
-
matchedOriginalIndices.add(origPara.originalIndex);
|
|
38
|
-
matchedRevisedIndices.add(revPara.originalIndex);
|
|
39
|
-
revisedToOriginal.set(revPara.originalIndex, origPara);
|
|
40
|
-
}
|
|
41
|
-
// Build output in revised document order
|
|
42
|
-
// For each position in the revised document, we output:
|
|
43
|
-
// 1. Any deleted paragraphs that came before the matching original
|
|
44
|
-
// 2. The matched/inserted paragraph
|
|
45
|
-
let lastOriginalIndex = -1;
|
|
46
|
-
for (let revIdx = 0; revIdx < revisedParagraphs.length; revIdx++) {
|
|
47
|
-
const revPara = revisedParagraphs[revIdx];
|
|
48
|
-
if (matchedRevisedIndices.has(revIdx)) {
|
|
49
|
-
// This is a matched paragraph
|
|
50
|
-
const origPara = revisedToOriginal.get(revIdx);
|
|
51
|
-
// First, output any deleted paragraphs between last and this
|
|
52
|
-
for (let i = lastOriginalIndex + 1; i < origPara.originalIndex; i++) {
|
|
53
|
-
if (!matchedOriginalIndices.has(i)) {
|
|
54
|
-
const deletedPara = originalByIndex.get(i);
|
|
55
|
-
if (deletedPara) {
|
|
56
|
-
operations.push({
|
|
57
|
-
type: 'deleted',
|
|
58
|
-
xml: generateDeletedParagraph(deletedPara.runs, author, date, extractPPrContent(deletedPara.pPrXml)),
|
|
59
|
-
originalIndex: i,
|
|
60
|
-
});
|
|
61
|
-
}
|
|
62
|
-
}
|
|
63
|
-
}
|
|
64
|
-
// Check if paragraphs are identical or modified
|
|
65
|
-
const similarity = alignment.matched.find(m => m.revised.originalIndex === revIdx)?.similarity ?? 0;
|
|
66
|
-
if (similarity >= 0.9999) {
|
|
67
|
-
// Unchanged paragraph - use revised content as-is
|
|
68
|
-
operations.push({
|
|
69
|
-
type: 'unchanged',
|
|
70
|
-
xml: generateParagraphXml(revPara),
|
|
71
|
-
originalIndex: origPara.originalIndex,
|
|
72
|
-
revisedIndex: revIdx,
|
|
73
|
-
});
|
|
74
|
-
}
|
|
75
|
-
else {
|
|
76
|
-
// Modified paragraph - diff the runs
|
|
77
|
-
const diffResult = diffRuns(origPara.runs, revPara.runs);
|
|
78
|
-
const trackChangesContent = renderTrackChanges(diffResult.mergedRuns, {
|
|
79
|
-
author,
|
|
80
|
-
date,
|
|
81
|
-
});
|
|
82
|
-
operations.push({
|
|
83
|
-
type: 'modified',
|
|
84
|
-
xml: wrapInParagraph(trackChangesContent, extractPPrContent(revPara.pPrXml)),
|
|
85
|
-
originalIndex: origPara.originalIndex,
|
|
86
|
-
revisedIndex: revIdx,
|
|
87
|
-
});
|
|
88
|
-
}
|
|
89
|
-
lastOriginalIndex = origPara.originalIndex;
|
|
90
|
-
}
|
|
91
|
-
else {
|
|
92
|
-
// This is an inserted paragraph
|
|
93
|
-
operations.push({
|
|
94
|
-
type: 'inserted',
|
|
95
|
-
xml: generateInsertedParagraph(revPara.runs, author, date, extractPPrContent(revPara.pPrXml)),
|
|
96
|
-
revisedIndex: revIdx,
|
|
97
|
-
});
|
|
98
|
-
}
|
|
99
|
-
}
|
|
100
|
-
// Output any remaining deleted paragraphs at the end
|
|
101
|
-
for (let i = lastOriginalIndex + 1; i < originalParagraphs.length; i++) {
|
|
102
|
-
if (!matchedOriginalIndices.has(i)) {
|
|
103
|
-
const deletedPara = originalByIndex.get(i);
|
|
104
|
-
if (deletedPara) {
|
|
105
|
-
operations.push({
|
|
106
|
-
type: 'deleted',
|
|
107
|
-
xml: generateDeletedParagraph(deletedPara.runs, author, date, extractPPrContent(deletedPara.pPrXml)),
|
|
108
|
-
originalIndex: i,
|
|
109
|
-
});
|
|
110
|
-
}
|
|
111
|
-
}
|
|
112
|
-
}
|
|
113
|
-
return operations;
|
|
114
|
-
}
|
|
115
|
-
/**
|
|
116
|
-
* Build a new document.xml with track changes applied.
|
|
117
|
-
*
|
|
118
|
-
* @param originalXml - The original document.xml content
|
|
119
|
-
* @param operations - Ordered list of paragraph operations
|
|
120
|
-
* @returns The new document.xml content
|
|
121
|
-
*/
|
|
122
|
-
export function buildDocumentWithTrackChanges(originalXml, operations) {
|
|
123
|
-
// Extract document structure
|
|
124
|
-
const { beforeBody, bodyContent, afterBody } = getDocumentParts(originalXml);
|
|
125
|
-
// Extract sectPr from body (must be preserved at end)
|
|
126
|
-
const { sectPr } = extractSectPr(bodyContent);
|
|
127
|
-
// Build new body content from operations
|
|
128
|
-
const paragraphXmls = operations.map(op => op.xml);
|
|
129
|
-
// Combine: paragraphs + sectPr (if present) + closing
|
|
130
|
-
let newBodyContent = paragraphXmls.join('\n');
|
|
131
|
-
if (sectPr) {
|
|
132
|
-
newBodyContent += '\n' + sectPr;
|
|
133
|
-
}
|
|
134
|
-
// Reconstruct document
|
|
135
|
-
return beforeBody + newBodyContent + afterBody;
|
|
136
|
-
}
|
|
137
|
-
/**
|
|
138
|
-
* Extract document parts for reconstruction.
|
|
139
|
-
*/
|
|
140
|
-
function getDocumentParts(documentXml) {
|
|
141
|
-
// Find w:body opening and closing
|
|
142
|
-
const bodyOpenMatch = documentXml.match(/<w:body[^>]*>/);
|
|
143
|
-
const bodyCloseMatch = documentXml.match(/<\/w:body>/);
|
|
144
|
-
if (!bodyOpenMatch || !bodyCloseMatch) {
|
|
145
|
-
return {
|
|
146
|
-
beforeBody: documentXml,
|
|
147
|
-
bodyContent: '',
|
|
148
|
-
afterBody: '',
|
|
149
|
-
};
|
|
150
|
-
}
|
|
151
|
-
const bodyOpenEnd = documentXml.indexOf(bodyOpenMatch[0]) + bodyOpenMatch[0].length;
|
|
152
|
-
const bodyCloseStart = documentXml.lastIndexOf('</w:body>');
|
|
153
|
-
return {
|
|
154
|
-
beforeBody: documentXml.slice(0, bodyOpenEnd),
|
|
155
|
-
bodyContent: documentXml.slice(bodyOpenEnd, bodyCloseStart),
|
|
156
|
-
afterBody: documentXml.slice(bodyCloseStart),
|
|
157
|
-
};
|
|
158
|
-
}
|
|
159
|
-
/**
|
|
160
|
-
* Generate XML for an unchanged paragraph.
|
|
161
|
-
*/
|
|
162
|
-
function generateParagraphXml(para) {
|
|
163
|
-
// Build paragraph from runs
|
|
164
|
-
const runsXml = para.runs.map(run => generateRunXml(run)).join('');
|
|
165
|
-
const pPr = para.pPrXml ? para.pPrXml : '';
|
|
166
|
-
return `<w:p>${pPr}${runsXml}</w:p>`;
|
|
167
|
-
}
|
|
168
|
-
/**
|
|
169
|
-
* Generate XML for a single run.
|
|
170
|
-
*/
|
|
171
|
-
function generateRunXml(run) {
|
|
172
|
-
const rPr = generateRunPropertiesXml(run.properties);
|
|
173
|
-
// Handle whitespace preservation
|
|
174
|
-
const needsSpace = run.text.startsWith(' ') || run.text.endsWith(' ') || run.text.includes(' ');
|
|
175
|
-
const spaceAttr = needsSpace ? ' xml:space="preserve"' : '';
|
|
176
|
-
return `<w:r>${rPr}<w:t${spaceAttr}>${escapeXml(run.text)}</w:t></w:r>`;
|
|
177
|
-
}
|
|
178
|
-
/**
|
|
179
|
-
* Generate run properties XML.
|
|
180
|
-
*/
|
|
181
|
-
function generateRunPropertiesXml(props) {
|
|
182
|
-
if (!props)
|
|
183
|
-
return '';
|
|
184
|
-
const parts = [];
|
|
185
|
-
if (props.bold)
|
|
186
|
-
parts.push('<w:b/>');
|
|
187
|
-
if (props.italic)
|
|
188
|
-
parts.push('<w:i/>');
|
|
189
|
-
if (props.underline)
|
|
190
|
-
parts.push(`<w:u w:val="${escapeXml(props.underline)}"/>`);
|
|
191
|
-
if (props.strikethrough)
|
|
192
|
-
parts.push('<w:strike/>');
|
|
193
|
-
if (props.highlight)
|
|
194
|
-
parts.push(`<w:highlight w:val="${escapeXml(props.highlight)}"/>`);
|
|
195
|
-
if (props.color)
|
|
196
|
-
parts.push(`<w:color w:val="${escapeXml(props.color)}"/>`);
|
|
197
|
-
if (props.fontSize !== undefined)
|
|
198
|
-
parts.push(`<w:sz w:val="${props.fontSize}"/>`);
|
|
199
|
-
if (props.fontFamily)
|
|
200
|
-
parts.push(`<w:rFonts w:ascii="${escapeXml(props.fontFamily)}" w:hAnsi="${escapeXml(props.fontFamily)}"/>`);
|
|
201
|
-
if (parts.length === 0)
|
|
202
|
-
return '';
|
|
203
|
-
return `<w:rPr>${parts.join('')}</w:rPr>`;
|
|
204
|
-
}
|
|
205
|
-
/**
|
|
206
|
-
* Extract inner pPr content from full pPr XML.
|
|
207
|
-
* Removes the outer <w:pPr> tags.
|
|
208
|
-
*/
|
|
209
|
-
function extractPPrContent(pPrXml) {
|
|
210
|
-
if (!pPrXml)
|
|
211
|
-
return undefined;
|
|
212
|
-
// Remove outer tags
|
|
213
|
-
const match = pPrXml.match(/<w:pPr[^>]*>([\s\S]*)<\/w:pPr>/);
|
|
214
|
-
return match ? match[1] : undefined;
|
|
215
|
-
}
|
|
216
|
-
/**
|
|
217
|
-
* Escape XML special characters.
|
|
218
|
-
*/
|
|
219
|
-
function escapeXml(text) {
|
|
220
|
-
return text
|
|
221
|
-
.replace(/&/g, '&')
|
|
222
|
-
.replace(/</g, '<')
|
|
223
|
-
.replace(/>/g, '>')
|
|
224
|
-
.replace(/"/g, '"')
|
|
225
|
-
.replace(/'/g, ''');
|
|
226
|
-
}
|
|
227
|
-
//# sourceMappingURL=documentBuilder.js.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"documentBuilder.js","sourceRoot":"","sources":["../../../src/baselines/diffmatch/documentBuilder.ts"],"names":[],"mappings":"AAAA;;;;;GAKG;AAGH,OAAO,EAAE,QAAQ,EAAE,MAAM,cAAc,CAAC;AACxC,OAAO,EACL,kBAAkB,EAClB,wBAAwB,EACxB,yBAAyB,EACzB,eAAe,GAChB,MAAM,2BAA2B,CAAC;AACnC,OAAO,EAAE,aAAa,EAA8B,MAAM,gBAAgB,CAAC;AAwB3E;;;;;GAKG;AACH,MAAM,UAAU,2BAA2B,CACzC,SAA0B,EAC1B,kBAA2C,EAC3C,iBAA0C,EAC1C,OAAqB;IAErB,MAAM,UAAU,GAAyB,EAAE,CAAC;IAC5C,MAAM,EAAE,MAAM,EAAE,IAAI,EAAE,GAAG,OAAO,CAAC;IAEjC,qDAAqD;IACrD,MAAM,eAAe,GAAG,IAAI,GAAG,EAAiC,CAAC;IACjE,KAAK,MAAM,CAAC,IAAI,kBAAkB,EAAE,CAAC;QACnC,eAAe,CAAC,GAAG,CAAC,CAAC,CAAC,aAAa,EAAE,CAAC,CAAC,CAAC;IAC1C,CAAC;IAED,oDAAoD;IACpD,MAAM,cAAc,GAAG,IAAI,GAAG,EAAiC,CAAC;IAChE,KAAK,MAAM,CAAC,IAAI,iBAAiB,EAAE,CAAC;QAClC,cAAc,CAAC,GAAG,CAAC,CAAC,CAAC,aAAa,EAAE,CAAC,CAAC,CAAC;IACzC,CAAC;IAED,oDAAoD;IACpD,MAAM,sBAAsB,GAAG,IAAI,GAAG,EAAU,CAAC;IACjD,MAAM,qBAAqB,GAAG,IAAI,GAAG,EAAU,CAAC;IAEhD,oEAAoE;IACpE,MAAM,iBAAiB,GAAG,IAAI,GAAG,EAAiC,CAAC;IAEnE,KAAK,MAAM,KAAK,IAAI,SAAS,CAAC,OAAO,EAAE,CAAC;QACtC,MAAM,QAAQ,GAAG,KAAK,CAAC,QAAiC,CAAC;QACzD,MAAM,OAAO,GAAG,KAAK,CAAC,OAAgC,CAAC;QAEvD,sBAAsB,CAAC,GAAG,CAAC,QAAQ,CAAC,aAAa,CAAC,CAAC;QACnD,qBAAqB,CAAC,GAAG,CAAC,OAAO,CAAC,aAAa,CAAC,CAAC;QACjD,iBAAiB,CAAC,GAAG,CAAC,OAAO,CAAC,aAAa,EAAE,QAAQ,CAAC,CAAC;IACzD,CAAC;IAED,yCAAyC;IACzC,wDAAwD;IACxD,mEAAmE;IACnE,oCAAoC;IAEpC,IAAI,iBAAiB,GAAG,CAAC,CAAC,CAAC;IAE3B,KAAK,IAAI,MAAM,GAAG,CAAC,EAAE,MAAM,GAAG,iBAAiB,CAAC,MAAM,EAAE,MAAM,EAAE,EAAE,CAAC;QACjE,MAAM,OAAO,GAAG,iBAAiB,CAAC,MAAM,CAAE,CAAC;QAE3C,IAAI,qBAAqB,CAAC,GAAG,CAAC,MAAM,CAAC,EAAE,CAAC;YACtC,8BAA8B;YAC9B,MAAM,QAAQ,GAAG,iBAAiB,CAAC,GAAG,CAAC,MAAM,CAAE,CAAC;YAEhD,6DAA6D;YAC7D,KAAK,IAAI,CAAC,GAAG,iBAAiB,GAAG,CAAC,EAAE,CAAC,GAAG,QAAQ,CAAC,aAAa,EAAE,CAAC,EAAE,EAAE,CAAC;gBACpE,IAAI,CAAC,sBAAsB,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,CAAC;oBACnC,MAAM,WAAW,GAAG,eAAe,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC;oBAC3C,IAAI,WAAW,EAAE,CAAC;wBAChB,UAAU,CAAC,IAAI,CAAC;4BACd,IAAI,EAAE,SAAS;4BACf,GAAG,EAAE,wBAAwB,CAC3B,WAAW,CAAC,IAAI,EAChB,MAAM,EACN,IAAI,EACJ,iBAAiB,CAAC,WAAW,CAAC,MAAM,CAAC,CACtC;4BACD,aAAa,EAAE,CAAC;yBACjB,CAAC,CAAC;oBACL,CAAC;gBACH,CAAC;YACH,CAAC;YAED,gDAAgD;YAChD,MAAM,UAAU,GAAG,SAAS,CAAC,OAAO,CAAC,IAAI,CACvC,CAAC,CAAC,EAAE,CAAE,CAAC,CAAC,OAAiC,CAAC,aAAa,KAAK,MAAM,CACnE,EAAE,UAAU,IAAI,CAAC,CAAC;YAEnB,IAAI,UAAU,IAAI,MAAM,EAAE,CAAC;gBACzB,kDAAkD;gBAClD,UAAU,CAAC,IAAI,CAAC;oBACd,IAAI,EAAE,WAAW;oBACjB,GAAG,EAAE,oBAAoB,CAAC,OAAO,CAAC;oBAClC,aAAa,EAAE,QAAQ,CAAC,aAAa;oBACrC,YAAY,EAAE,MAAM;iBACrB,CAAC,CAAC;YACL,CAAC;iBAAM,CAAC;gBACN,qCAAqC;gBACrC,MAAM,UAAU,GAAG,QAAQ,CAAC,QAAQ,CAAC,IAAI,EAAE,OAAO,CAAC,IAAI,CAAC,CAAC;gBACzD,MAAM,mBAAmB,GAAG,kBAAkB,CAAC,UAAU,CAAC,UAAU,EAAE;oBACpE,MAAM;oBACN,IAAI;iBACL,CAAC,CAAC;gBAEH,UAAU,CAAC,IAAI,CAAC;oBACd,IAAI,EAAE,UAAU;oBAChB,GAAG,EAAE,eAAe,CAAC,mBAAmB,EAAE,iBAAiB,CAAC,OAAO,CAAC,MAAM,CAAC,CAAC;oBAC5E,aAAa,EAAE,QAAQ,CAAC,aAAa;oBACrC,YAAY,EAAE,MAAM;iBACrB,CAAC,CAAC;YACL,CAAC;YAED,iBAAiB,GAAG,QAAQ,CAAC,aAAa,CAAC;QAC7C,CAAC;aAAM,CAAC;YACN,gCAAgC;YAChC,UAAU,CAAC,IAAI,CAAC;gBACd,IAAI,EAAE,UAAU;gBAChB,GAAG,EAAE,yBAAyB,CAC5B,OAAO,CAAC,IAAI,EACZ,MAAM,EACN,IAAI,EACJ,iBAAiB,CAAC,OAAO,CAAC,MAAM,CAAC,CAClC;gBACD,YAAY,EAAE,MAAM;aACrB,CAAC,CAAC;QACL,CAAC;IACH,CAAC;IAED,qDAAqD;IACrD,KAAK,IAAI,CAAC,GAAG,iBAAiB,GAAG,CAAC,EAAE,CAAC,GAAG,kBAAkB,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;QACvE,IAAI,CAAC,sBAAsB,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,CAAC;YACnC,MAAM,WAAW,GAAG,eAAe,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC;YAC3C,IAAI,WAAW,EAAE,CAAC;gBAChB,UAAU,CAAC,IAAI,CAAC;oBACd,IAAI,EAAE,SAAS;oBACf,GAAG,EAAE,wBAAwB,CAC3B,WAAW,CAAC,IAAI,EAChB,MAAM,EACN,IAAI,EACJ,iBAAiB,CAAC,WAAW,CAAC,MAAM,CAAC,CACtC;oBACD,aAAa,EAAE,CAAC;iBACjB,CAAC,CAAC;YACL,CAAC;QACH,CAAC;IACH,CAAC;IAED,OAAO,UAAU,CAAC;AACpB,CAAC;AAED;;;;;;GAMG;AACH,MAAM,UAAU,6BAA6B,CAC3C,WAAmB,EACnB,UAAgC;IAEhC,6BAA6B;IAC7B,MAAM,EAAE,UAAU,EAAE,WAAW,EAAE,SAAS,EAAE,GAAG,gBAAgB,CAAC,WAAW,CAAC,CAAC;IAE7E,sDAAsD;IACtD,MAAM,EAAE,MAAM,EAAE,GAAG,aAAa,CAAC,WAAW,CAAC,CAAC;IAE9C,yCAAyC;IACzC,MAAM,aAAa,GAAG,UAAU,CAAC,GAAG,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,GAAG,CAAC,CAAC;IAEnD,sDAAsD;IACtD,IAAI,cAAc,GAAG,aAAa,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IAC9C,IAAI,MAAM,EAAE,CAAC;QACX,cAAc,IAAI,IAAI,GAAG,MAAM,CAAC;IAClC,CAAC;IAED,uBAAuB;IACvB,OAAO,UAAU,GAAG,cAAc,GAAG,SAAS,CAAC;AACjD,CAAC;AAED;;GAEG;AACH,SAAS,gBAAgB,CAAC,WAAmB;IAK3C,kCAAkC;IAClC,MAAM,aAAa,GAAG,WAAW,CAAC,KAAK,CAAC,eAAe,CAAC,CAAC;IACzD,MAAM,cAAc,GAAG,WAAW,CAAC,KAAK,CAAC,YAAY,CAAC,CAAC;IAEvD,IAAI,CAAC,aAAa,IAAI,CAAC,cAAc,EAAE,CAAC;QACtC,OAAO;YACL,UAAU,EAAE,WAAW;YACvB,WAAW,EAAE,EAAE;YACf,SAAS,EAAE,EAAE;SACd,CAAC;IACJ,CAAC;IAED,MAAM,WAAW,GAAG,WAAW,CAAC,OAAO,CAAC,aAAa,CAAC,CAAC,CAAC,CAAC,GAAG,aAAa,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC;IACpF,MAAM,cAAc,GAAG,WAAW,CAAC,WAAW,CAAC,WAAW,CAAC,CAAC;IAE5D,OAAO;QACL,UAAU,EAAE,WAAW,CAAC,KAAK,CAAC,CAAC,EAAE,WAAW,CAAC;QAC7C,WAAW,EAAE,WAAW,CAAC,KAAK,CAAC,WAAW,EAAE,cAAc,CAAC;QAC3D,SAAS,EAAE,WAAW,CAAC,KAAK,CAAC,cAAc,CAAC;KAC7C,CAAC;AACJ,CAAC;AAED;;GAEG;AACH,SAAS,oBAAoB,CAAC,IAA2B;IACvD,4BAA4B;IAC5B,MAAM,OAAO,GAAG,IAAI,CAAC,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC,EAAE,CAAC,cAAc,CAAC,GAAG,CAAC,CAAC,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;IACnE,MAAM,GAAG,GAAG,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,CAAC;IAE3C,OAAO,QAAQ,GAAG,GAAG,OAAO,QAAQ,CAAC;AACvC,CAAC;AAED;;GAEG;AACH,SAAS,cAAc,CAAC,GAAY;IAClC,MAAM,GAAG,GAAG,wBAAwB,CAAC,GAAG,CAAC,UAAU,CAAC,CAAC;IAErD,iCAAiC;IACjC,MAAM,UAAU,GAAG,GAAG,CAAC,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,IAAI,GAAG,CAAC,IAAI,CAAC,QAAQ,CAAC,GAAG,CAAC,IAAI,GAAG,CAAC,IAAI,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC;IACjG,MAAM,SAAS,GAAG,UAAU,CAAC,CAAC,CAAC,uBAAuB,CAAC,CAAC,CAAC,EAAE,CAAC;IAE5D,OAAO,QAAQ,GAAG,OAAO,SAAS,IAAI,SAAS,CAAC,GAAG,CAAC,IAAI,CAAC,cAAc,CAAC;AAC1E,CAAC;AAED;;GAEG;AACH,SAAS,wBAAwB,CAAC,KAA2D;IAC3F,IAAI,CAAC,KAAK;QAAE,OAAO,EAAE,CAAC;IAEtB,MAAM,KAAK,GAAa,EAAE,CAAC;IAE3B,IAAI,KAAK,CAAC,IAAI;QAAE,KAAK,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC;IACrC,IAAI,KAAK,CAAC,MAAM;QAAE,KAAK,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC;IACvC,IAAI,KAAK,CAAC,SAAS;QAAE,KAAK,CAAC,IAAI,CAAC,eAAe,SAAS,CAAC,KAAK,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC;IAChF,IAAI,KAAK,CAAC,aAAa;QAAE,KAAK,CAAC,IAAI,CAAC,aAAa,CAAC,CAAC;IACnD,IAAI,KAAK,CAAC,SAAS;QAAE,KAAK,CAAC,IAAI,CAAC,uBAAuB,SAAS,CAAC,KAAK,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC;IACxF,IAAI,KAAK,CAAC,KAAK;QAAE,KAAK,CAAC,IAAI,CAAC,mBAAmB,SAAS,CAAC,KAAK,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC;IAC5E,IAAI,KAAK,CAAC,QAAQ,KAAK,SAAS;QAAE,KAAK,CAAC,IAAI,CAAC,gBAAgB,KAAK,CAAC,QAAQ,KAAK,CAAC,CAAC;IAClF,IAAI,KAAK,CAAC,UAAU;QAAE,KAAK,CAAC,IAAI,CAAC,sBAAsB,SAAS,CAAC,KAAK,CAAC,UAAU,CAAC,cAAc,SAAS,CAAC,KAAK,CAAC,UAAU,CAAC,KAAK,CAAC,CAAC;IAElI,IAAI,KAAK,CAAC,MAAM,KAAK,CAAC;QAAE,OAAO,EAAE,CAAC;IAElC,OAAO,UAAU,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,UAAU,CAAC;AAC5C,CAAC;AAED;;;GAGG;AACH,SAAS,iBAAiB,CAAC,MAAe;IACxC,IAAI,CAAC,MAAM;QAAE,OAAO,SAAS,CAAC;IAE9B,oBAAoB;IACpB,MAAM,KAAK,GAAG,MAAM,CAAC,KAAK,CAAC,gCAAgC,CAAC,CAAC;IAC7D,OAAO,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;AACtC,CAAC;AAED;;GAEG;AACH,SAAS,SAAS,CAAC,IAAY;IAC7B,OAAO,IAAI;SACR,OAAO,CAAC,IAAI,EAAE,OAAO,CAAC;SACtB,OAAO,CAAC,IAAI,EAAE,MAAM,CAAC;SACrB,OAAO,CAAC,IAAI,EAAE,MAAM,CAAC;SACrB,OAAO,CAAC,IAAI,EAAE,QAAQ,CAAC;SACvB,OAAO,CAAC,IAAI,EAAE,QAAQ,CAAC,CAAC;AAC7B,CAAC"}
|
|
@@ -1,75 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* Baseline B: Paragraph alignment using LCS (Longest Common Subsequence).
|
|
3
|
-
*
|
|
4
|
-
* Aligns paragraphs between original and revised documents to identify:
|
|
5
|
-
* - Matched paragraphs (same or similar content)
|
|
6
|
-
* - Inserted paragraphs (only in revised)
|
|
7
|
-
* - Deleted paragraphs (only in original)
|
|
8
|
-
* - Modified paragraphs (matched but with differences)
|
|
9
|
-
*/
|
|
10
|
-
import type { ParagraphInfo, AlignmentResult } from '../../shared/ooxml/types.js';
|
|
11
|
-
/**
|
|
12
|
-
* Compute a hash for a paragraph's normalized text.
|
|
13
|
-
*
|
|
14
|
-
* Used for fast comparison during LCS.
|
|
15
|
-
*/
|
|
16
|
-
export declare function hashParagraph(text: string): string;
|
|
17
|
-
/**
|
|
18
|
-
* Normalize paragraph text for comparison.
|
|
19
|
-
*
|
|
20
|
-
* - Trim whitespace
|
|
21
|
-
* - Collapse multiple spaces
|
|
22
|
-
* - Lowercase for case-insensitive comparison
|
|
23
|
-
*/
|
|
24
|
-
export declare function normalizeParagraphText(text: string): string;
|
|
25
|
-
/**
|
|
26
|
-
* Compute similarity between two strings using Jaccard index on words.
|
|
27
|
-
*
|
|
28
|
-
* @returns Value between 0 (completely different) and 1 (identical)
|
|
29
|
-
*/
|
|
30
|
-
export declare function computeSimilarity(a: string, b: string): number;
|
|
31
|
-
/**
|
|
32
|
-
* Compute the Longest Common Subsequence of two arrays using dynamic programming.
|
|
33
|
-
*
|
|
34
|
-
* @param a - First array
|
|
35
|
-
* @param b - Second array
|
|
36
|
-
* @param keyFn - Function to extract comparison key from elements
|
|
37
|
-
* @returns Array of [indexA, indexB] pairs representing the LCS
|
|
38
|
-
*/
|
|
39
|
-
export declare function lcs<T>(a: T[], b: T[], keyFn: (item: T) => string): Array<[number, number]>;
|
|
40
|
-
/**
|
|
41
|
-
* Align paragraphs between original and revised documents.
|
|
42
|
-
*
|
|
43
|
-
* Uses hash-based LCS to find matching paragraphs, then classifies
|
|
44
|
-
* unmatched paragraphs as inserted or deleted.
|
|
45
|
-
*
|
|
46
|
-
* @param original - Paragraphs from original document
|
|
47
|
-
* @param revised - Paragraphs from revised document
|
|
48
|
-
* @param similarityThreshold - Minimum similarity to consider a match (default: 0.5)
|
|
49
|
-
*/
|
|
50
|
-
export declare function alignParagraphs(original: ParagraphInfo[], revised: ParagraphInfo[], similarityThreshold?: number): AlignmentResult;
|
|
51
|
-
/**
|
|
52
|
-
* Classify paragraph matches into categories.
|
|
53
|
-
*/
|
|
54
|
-
export interface ParagraphClassification {
|
|
55
|
-
/** Identical paragraphs (similarity = 1.0) */
|
|
56
|
-
identical: Array<{
|
|
57
|
-
original: ParagraphInfo;
|
|
58
|
-
revised: ParagraphInfo;
|
|
59
|
-
}>;
|
|
60
|
-
/** Modified paragraphs (0 < similarity < 1.0) */
|
|
61
|
-
modified: Array<{
|
|
62
|
-
original: ParagraphInfo;
|
|
63
|
-
revised: ParagraphInfo;
|
|
64
|
-
similarity: number;
|
|
65
|
-
}>;
|
|
66
|
-
/** Deleted paragraphs */
|
|
67
|
-
deleted: ParagraphInfo[];
|
|
68
|
-
/** Inserted paragraphs */
|
|
69
|
-
inserted: ParagraphInfo[];
|
|
70
|
-
}
|
|
71
|
-
/**
|
|
72
|
-
* Classify alignment result into more granular categories.
|
|
73
|
-
*/
|
|
74
|
-
export declare function classifyAlignment(alignment: AlignmentResult): ParagraphClassification;
|
|
75
|
-
//# sourceMappingURL=paragraphAlignment.d.ts.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"paragraphAlignment.d.ts","sourceRoot":"","sources":["../../../src/baselines/diffmatch/paragraphAlignment.ts"],"names":[],"mappings":"AAAA;;;;;;;;GAQG;AAGH,OAAO,KAAK,EAAE,aAAa,EAAE,eAAe,EAAE,MAAM,6BAA6B,CAAC;AAElF;;;;GAIG;AACH,wBAAgB,aAAa,CAAC,IAAI,EAAE,MAAM,GAAG,MAAM,CAGlD;AAED;;;;;;GAMG;AACH,wBAAgB,sBAAsB,CAAC,IAAI,EAAE,MAAM,GAAG,MAAM,CAK3D;AAED;;;;GAIG;AACH,wBAAgB,iBAAiB,CAAC,CAAC,EAAE,MAAM,EAAE,CAAC,EAAE,MAAM,GAAG,MAAM,CAe9D;AAED;;;;;;;GAOG;AACH,wBAAgB,GAAG,CAAC,CAAC,EACnB,CAAC,EAAE,CAAC,EAAE,EACN,CAAC,EAAE,CAAC,EAAE,EACN,KAAK,EAAE,CAAC,IAAI,EAAE,CAAC,KAAK,MAAM,GACzB,KAAK,CAAC,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC,CAqCzB;AAED;;;;;;;;;GASG;AACH,wBAAgB,eAAe,CAC7B,QAAQ,EAAE,aAAa,EAAE,EACzB,OAAO,EAAE,aAAa,EAAE,EACxB,mBAAmB,SAAM,GACxB,eAAe,CA6FjB;AAED;;GAEG;AACH,MAAM,WAAW,uBAAuB;IACtC,8CAA8C;IAC9C,SAAS,EAAE,KAAK,CAAC;QAAE,QAAQ,EAAE,aAAa,CAAC;QAAC,OAAO,EAAE,aAAa,CAAA;KAAE,CAAC,CAAC;IACtE,iDAAiD;IACjD,QAAQ,EAAE,KAAK,CAAC;QACd,QAAQ,EAAE,aAAa,CAAC;QACxB,OAAO,EAAE,aAAa,CAAC;QACvB,UAAU,EAAE,MAAM,CAAC;KACpB,CAAC,CAAC;IACH,yBAAyB;IACzB,OAAO,EAAE,aAAa,EAAE,CAAC;IACzB,0BAA0B;IAC1B,QAAQ,EAAE,aAAa,EAAE,CAAC;CAC3B;AAED;;GAEG;AACH,wBAAgB,iBAAiB,CAAC,SAAS,EAAE,eAAe,GAAG,uBAAuB,CAoBrF"}
|