@intentic/fileq 1.317.0

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.
Files changed (184) hide show
  1. package/LICENSE +21 -0
  2. package/README.md +46 -0
  3. package/dist/app.d.ts +2 -0
  4. package/dist/app.d.ts.map +1 -0
  5. package/dist/app.js +43 -0
  6. package/dist/app.js.map +1 -0
  7. package/dist/cli.d.ts +3 -0
  8. package/dist/cli.d.ts.map +1 -0
  9. package/dist/cli.js +4 -0
  10. package/dist/cli.js.map +1 -0
  11. package/dist/commands/derive.command.d.ts +5 -0
  12. package/dist/commands/derive.command.d.ts.map +1 -0
  13. package/dist/commands/derive.command.js +53 -0
  14. package/dist/commands/derive.command.js.map +1 -0
  15. package/dist/commands/git-attributes.command.d.ts +3 -0
  16. package/dist/commands/git-attributes.command.d.ts.map +1 -0
  17. package/dist/commands/git-attributes.command.js +12 -0
  18. package/dist/commands/git-attributes.command.js.map +1 -0
  19. package/dist/commands/read.command.d.ts +3 -0
  20. package/dist/commands/read.command.d.ts.map +1 -0
  21. package/dist/commands/read.command.js +126 -0
  22. package/dist/commands/read.command.js.map +1 -0
  23. package/dist/commands/sweep.command.d.ts +3 -0
  24. package/dist/commands/sweep.command.d.ts.map +1 -0
  25. package/dist/commands/sweep.command.js +41 -0
  26. package/dist/commands/sweep.command.js.map +1 -0
  27. package/dist/lib/archives.d.ts +18 -0
  28. package/dist/lib/archives.d.ts.map +1 -0
  29. package/dist/lib/archives.js +133 -0
  30. package/dist/lib/archives.js.map +1 -0
  31. package/dist/lib/derive.d.ts +32 -0
  32. package/dist/lib/derive.d.ts.map +1 -0
  33. package/dist/lib/derive.js +99 -0
  34. package/dist/lib/derive.js.map +1 -0
  35. package/dist/lib/derivers/archive.d.ts +3 -0
  36. package/dist/lib/derivers/archive.d.ts.map +1 -0
  37. package/dist/lib/derivers/archive.js +132 -0
  38. package/dist/lib/derivers/archive.js.map +1 -0
  39. package/dist/lib/derivers/deriver.d.ts +13 -0
  40. package/dist/lib/derivers/deriver.d.ts.map +1 -0
  41. package/dist/lib/derivers/deriver.js +8 -0
  42. package/dist/lib/derivers/deriver.js.map +1 -0
  43. package/dist/lib/derivers/docx.d.ts +6 -0
  44. package/dist/lib/derivers/docx.d.ts.map +1 -0
  45. package/dist/lib/derivers/docx.js +29 -0
  46. package/dist/lib/derivers/docx.js.map +1 -0
  47. package/dist/lib/derivers/epub.d.ts +3 -0
  48. package/dist/lib/derivers/epub.d.ts.map +1 -0
  49. package/dist/lib/derivers/epub.js +102 -0
  50. package/dist/lib/derivers/epub.js.map +1 -0
  51. package/dist/lib/derivers/html.d.ts +3 -0
  52. package/dist/lib/derivers/html.d.ts.map +1 -0
  53. package/dist/lib/derivers/html.js +18 -0
  54. package/dist/lib/derivers/html.js.map +1 -0
  55. package/dist/lib/derivers/image.d.ts +3 -0
  56. package/dist/lib/derivers/image.d.ts.map +1 -0
  57. package/dist/lib/derivers/image.js +42 -0
  58. package/dist/lib/derivers/image.js.map +1 -0
  59. package/dist/lib/derivers/ipynb.d.ts +3 -0
  60. package/dist/lib/derivers/ipynb.d.ts.map +1 -0
  61. package/dist/lib/derivers/ipynb.js +75 -0
  62. package/dist/lib/derivers/ipynb.js.map +1 -0
  63. package/dist/lib/derivers/media.d.ts +3 -0
  64. package/dist/lib/derivers/media.d.ts.map +1 -0
  65. package/dist/lib/derivers/media.js +45 -0
  66. package/dist/lib/derivers/media.js.map +1 -0
  67. package/dist/lib/derivers/odp.d.ts +3 -0
  68. package/dist/lib/derivers/odp.d.ts.map +1 -0
  69. package/dist/lib/derivers/odp.js +41 -0
  70. package/dist/lib/derivers/odp.js.map +1 -0
  71. package/dist/lib/derivers/ods.d.ts +3 -0
  72. package/dist/lib/derivers/ods.d.ts.map +1 -0
  73. package/dist/lib/derivers/ods.js +86 -0
  74. package/dist/lib/derivers/ods.js.map +1 -0
  75. package/dist/lib/derivers/odt.d.ts +4 -0
  76. package/dist/lib/derivers/odt.d.ts.map +1 -0
  77. package/dist/lib/derivers/odt.js +77 -0
  78. package/dist/lib/derivers/odt.js.map +1 -0
  79. package/dist/lib/derivers/pdf-furniture.d.ts +7 -0
  80. package/dist/lib/derivers/pdf-furniture.d.ts.map +1 -0
  81. package/dist/lib/derivers/pdf-furniture.js +76 -0
  82. package/dist/lib/derivers/pdf-furniture.js.map +1 -0
  83. package/dist/lib/derivers/pdf.d.ts +4 -0
  84. package/dist/lib/derivers/pdf.d.ts.map +1 -0
  85. package/dist/lib/derivers/pdf.js +79 -0
  86. package/dist/lib/derivers/pdf.js.map +1 -0
  87. package/dist/lib/derivers/pptx.d.ts +4 -0
  88. package/dist/lib/derivers/pptx.d.ts.map +1 -0
  89. package/dist/lib/derivers/pptx.js +51 -0
  90. package/dist/lib/derivers/pptx.js.map +1 -0
  91. package/dist/lib/derivers/profile.d.ts +3 -0
  92. package/dist/lib/derivers/profile.d.ts.map +1 -0
  93. package/dist/lib/derivers/profile.js +115 -0
  94. package/dist/lib/derivers/profile.js.map +1 -0
  95. package/dist/lib/derivers/rtf.d.ts +4 -0
  96. package/dist/lib/derivers/rtf.d.ts.map +1 -0
  97. package/dist/lib/derivers/rtf.js +187 -0
  98. package/dist/lib/derivers/rtf.js.map +1 -0
  99. package/dist/lib/derivers/xlsx.d.ts +3 -0
  100. package/dist/lib/derivers/xlsx.d.ts.map +1 -0
  101. package/dist/lib/derivers/xlsx.js +68 -0
  102. package/dist/lib/derivers/xlsx.js.map +1 -0
  103. package/dist/lib/env.d.ts +2 -0
  104. package/dist/lib/env.d.ts.map +1 -0
  105. package/dist/lib/env.js +5 -0
  106. package/dist/lib/env.js.map +1 -0
  107. package/dist/lib/flags.d.ts +2 -0
  108. package/dist/lib/flags.d.ts.map +1 -0
  109. package/dist/lib/flags.js +8 -0
  110. package/dist/lib/flags.js.map +1 -0
  111. package/dist/lib/formats.d.ts +6 -0
  112. package/dist/lib/formats.d.ts.map +1 -0
  113. package/dist/lib/formats.js +110 -0
  114. package/dist/lib/formats.js.map +1 -0
  115. package/dist/lib/sidecar.d.ts +30 -0
  116. package/dist/lib/sidecar.d.ts.map +1 -0
  117. package/dist/lib/sidecar.js +108 -0
  118. package/dist/lib/sidecar.js.map +1 -0
  119. package/dist/lib/sweep.d.ts +7 -0
  120. package/dist/lib/sweep.d.ts.map +1 -0
  121. package/dist/lib/sweep.js +56 -0
  122. package/dist/lib/sweep.js.map +1 -0
  123. package/dist/lib/tools.d.ts +2 -0
  124. package/dist/lib/tools.d.ts.map +1 -0
  125. package/dist/lib/tools.js +15 -0
  126. package/dist/lib/tools.js.map +1 -0
  127. package/dist/lib/xml.d.ts +3 -0
  128. package/dist/lib/xml.d.ts.map +1 -0
  129. package/dist/lib/xml.js +16 -0
  130. package/dist/lib/xml.js.map +1 -0
  131. package/dist/skill.d.ts +5 -0
  132. package/dist/skill.d.ts.map +1 -0
  133. package/dist/skill.js +75 -0
  134. package/dist/skill.js.map +1 -0
  135. package/dist/testing.d.ts +25 -0
  136. package/dist/testing.d.ts.map +1 -0
  137. package/dist/testing.js +220 -0
  138. package/dist/testing.js.map +1 -0
  139. package/dist/version.d.ts +2 -0
  140. package/dist/version.d.ts.map +1 -0
  141. package/dist/version.js +3 -0
  142. package/dist/version.js.map +1 -0
  143. package/package.json +89 -0
  144. package/src/app.ts +48 -0
  145. package/src/cli.integration.test.ts +200 -0
  146. package/src/cli.ts +6 -0
  147. package/src/commands/derive.command.ts +59 -0
  148. package/src/commands/git-attributes.command.ts +13 -0
  149. package/src/commands/read.command.ts +158 -0
  150. package/src/commands/sweep.command.ts +48 -0
  151. package/src/derivers.integration.test.ts +415 -0
  152. package/src/lib/archives.test.ts +72 -0
  153. package/src/lib/archives.ts +209 -0
  154. package/src/lib/derive.ts +132 -0
  155. package/src/lib/derivers/archive.ts +168 -0
  156. package/src/lib/derivers/deriver.ts +33 -0
  157. package/src/lib/derivers/docx.test.ts +38 -0
  158. package/src/lib/derivers/docx.ts +44 -0
  159. package/src/lib/derivers/epub.ts +130 -0
  160. package/src/lib/derivers/html.ts +21 -0
  161. package/src/lib/derivers/image.ts +54 -0
  162. package/src/lib/derivers/ipynb.ts +113 -0
  163. package/src/lib/derivers/load-cost.test.ts +44 -0
  164. package/src/lib/derivers/media.ts +51 -0
  165. package/src/lib/derivers/odp.ts +52 -0
  166. package/src/lib/derivers/ods.ts +104 -0
  167. package/src/lib/derivers/odt.ts +101 -0
  168. package/src/lib/derivers/pdf-furniture.test.ts +60 -0
  169. package/src/lib/derivers/pdf-furniture.ts +121 -0
  170. package/src/lib/derivers/pdf.ts +102 -0
  171. package/src/lib/derivers/pptx.ts +61 -0
  172. package/src/lib/derivers/profile.ts +172 -0
  173. package/src/lib/derivers/rtf.ts +233 -0
  174. package/src/lib/derivers/xlsx.ts +82 -0
  175. package/src/lib/env.ts +7 -0
  176. package/src/lib/formats.test.ts +50 -0
  177. package/src/lib/formats.ts +141 -0
  178. package/src/lib/sidecar.test.ts +60 -0
  179. package/src/lib/sidecar.ts +156 -0
  180. package/src/lib/sweep.ts +72 -0
  181. package/src/lib/tools.ts +16 -0
  182. package/src/lib/xml.ts +20 -0
  183. package/src/skill.ts +90 -0
  184. package/src/testing.ts +333 -0
@@ -0,0 +1,32 @@
1
+ import { type Format } from "./formats.js";
2
+ import { type DerivedDoc, type Deriver } from "./derivers/deriver.js";
3
+ export declare const DERIVERS: Record<Format, Deriver>;
4
+ export declare const MAX_SOURCE_BYTES: number;
5
+ export declare const relPathIn: (root: string, abs: string) => string | undefined;
6
+ export declare const isDeriveIgnored: (relPath: string) => boolean;
7
+ export type Outcome = {
8
+ readonly kind: "derived";
9
+ readonly relPath: string;
10
+ readonly format: Format;
11
+ readonly sidecarPath: string;
12
+ readonly body: string;
13
+ readonly doc: DerivedDoc;
14
+ readonly tokens: number;
15
+ } | {
16
+ readonly kind: "fresh";
17
+ readonly relPath: string;
18
+ readonly format: Format;
19
+ readonly sidecarPath: string;
20
+ readonly body: string;
21
+ readonly tokens: number;
22
+ } | {
23
+ readonly kind: "removed";
24
+ readonly relPath: string;
25
+ readonly sidecarPath: string;
26
+ } | {
27
+ readonly kind: "skipped";
28
+ readonly relPath: string;
29
+ readonly reason: string;
30
+ };
31
+ export declare const ensureSidecar: (workspaceRoot: string, absPath: string, now?: () => Date) => Promise<Outcome>;
32
+ //# sourceMappingURL=derive.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"derive.d.ts","sourceRoot":"","sources":["../../src/lib/derive.ts"],"names":[],"mappings":"AAOA,OAAO,EAAgB,KAAK,MAAM,EAAE,MAAM,cAAc,CAAC;AACzD,OAAO,EAA+B,KAAK,UAAU,EAAE,KAAK,OAAO,EAAE,MAAM,uBAAuB,CAAC;AAqBnG,eAAO,MAAM,QAAQ,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAgB5C,CAAC;AAGF,eAAO,MAAM,gBAAgB,QAAoB,CAAC;AAGlD,eAAO,MAAM,SAAS,SAAU,MAAM,OAAO,MAAM,KAAG,MAAM,GAAG,SAG9D,CAAC;AAGF,eAAO,MAAM,eAAe,YAAa,MAAM,KAAG,OAGjD,CAAC;AAEF,MAAM,MAAM,OAAO,GACb;IACI,QAAQ,CAAC,IAAI,EAAE,SAAS,CAAC;IACzB,QAAQ,CAAC,OAAO,EAAE,MAAM,CAAC;IACzB,QAAQ,CAAC,MAAM,EAAE,MAAM,CAAC;IACxB,QAAQ,CAAC,WAAW,EAAE,MAAM,CAAC;IAC7B,QAAQ,CAAC,IAAI,EAAE,MAAM,CAAC;IACtB,QAAQ,CAAC,GAAG,EAAE,UAAU,CAAC;IACzB,QAAQ,CAAC,MAAM,EAAE,MAAM,CAAC;CAC3B,GACD;IACI,QAAQ,CAAC,IAAI,EAAE,OAAO,CAAC;IACvB,QAAQ,CAAC,OAAO,EAAE,MAAM,CAAC;IACzB,QAAQ,CAAC,MAAM,EAAE,MAAM,CAAC;IACxB,QAAQ,CAAC,WAAW,EAAE,MAAM,CAAC;IAC7B,QAAQ,CAAC,IAAI,EAAE,MAAM,CAAC;IACtB,QAAQ,CAAC,MAAM,EAAE,MAAM,CAAC;CAC3B,GACD;IAAE,QAAQ,CAAC,IAAI,EAAE,SAAS,CAAC;IAAC,QAAQ,CAAC,OAAO,EAAE,MAAM,CAAC;IAAC,QAAQ,CAAC,WAAW,EAAE,MAAM,CAAA;CAAE,GACpF;IAAE,QAAQ,CAAC,IAAI,EAAE,SAAS,CAAC;IAAC,QAAQ,CAAC,OAAO,EAAE,MAAM,CAAC;IAAC,QAAQ,CAAC,MAAM,EAAE,MAAM,CAAA;CAAE,CAAC;AAGtF,eAAO,MAAM,aAAa,kBAAyB,MAAM,WAAW,MAAM,QAAO,MAAM,IAAI,KAAsB,OAAO,CAAC,OAAO,CA+C/H,CAAC"}
@@ -0,0 +1,99 @@
1
+ import { stat } from "node:fs/promises";
2
+ import { isAbsolute, relative, sep } from "node:path";
3
+ import { estimateTokens } from "@intentic/base/format";
4
+ import { errnoCode, errorMessage, isMissing } from "@intentic/base/errors";
5
+ import { IGNORED_DIRS, isAgentWorktreePath, isReferencePath } from "@intentic/workspace-ignore";
6
+ import { STATE_DIR } from "@intentic/constants";
7
+ import { detectFormat } from "./formats.js";
8
+ import { deriverStamp, neutralizeDoc } from "./derivers/deriver.js";
9
+ import { archiveDeriver } from "./derivers/archive.js";
10
+ import { docxDeriver } from "./derivers/docx.js";
11
+ import { epubDeriver } from "./derivers/epub.js";
12
+ import { htmlDeriver } from "./derivers/html.js";
13
+ import { imageDeriver } from "./derivers/image.js";
14
+ import { ipynbDeriver } from "./derivers/ipynb.js";
15
+ import { mediaDeriver } from "./derivers/media.js";
16
+ import { odpDeriver } from "./derivers/odp.js";
17
+ import { odsDeriver } from "./derivers/ods.js";
18
+ import { odtDeriver } from "./derivers/odt.js";
19
+ import { pdfDeriver } from "./derivers/pdf.js";
20
+ import { pptxDeriver } from "./derivers/pptx.js";
21
+ import { profileDeriver } from "./derivers/profile.js";
22
+ import { rtfDeriver } from "./derivers/rtf.js";
23
+ import { xlsxDeriver } from "./derivers/xlsx.js";
24
+ import { isFresh, readSidecar, removeSidecar, sidecarBody, sidecarPathFor, sha256OfFile, writeSidecar } from "./sidecar.js";
25
+ export const DERIVERS = {
26
+ docx: docxDeriver,
27
+ xlsx: xlsxDeriver,
28
+ pptx: pptxDeriver,
29
+ pdf: pdfDeriver,
30
+ image: imageDeriver,
31
+ media: mediaDeriver,
32
+ html: htmlDeriver,
33
+ ipynb: ipynbDeriver,
34
+ odt: odtDeriver,
35
+ ods: odsDeriver,
36
+ odp: odpDeriver,
37
+ rtf: rtfDeriver,
38
+ epub: epubDeriver,
39
+ archive: archiveDeriver,
40
+ profile: profileDeriver,
41
+ };
42
+ export const MAX_SOURCE_BYTES = 200 * 1024 * 1024;
43
+ export const relPathIn = (root, abs) => {
44
+ const rel = relative(root, abs);
45
+ return rel === "" || rel.startsWith("..") || isAbsolute(rel) ? undefined : rel.split(sep).join("/");
46
+ };
47
+ export const isDeriveIgnored = (relPath) => {
48
+ const segments = relPath.split("/");
49
+ return segments.some((segment) => IGNORED_DIRS.has(segment) || segment === STATE_DIR) || isReferencePath(relPath) || isAgentWorktreePath(relPath);
50
+ };
51
+ export const ensureSidecar = async (workspaceRoot, absPath, now = () => new Date()) => {
52
+ const relPath = relPathIn(workspaceRoot, absPath);
53
+ if (relPath === undefined) {
54
+ return { kind: "skipped", relPath: absPath, reason: "outside-workspace" };
55
+ }
56
+ if (isDeriveIgnored(relPath)) {
57
+ return { kind: "skipped", relPath, reason: "ignored-path" };
58
+ }
59
+ const sidecarPath = sidecarPathFor(workspaceRoot, relPath);
60
+ let source;
61
+ try {
62
+ source = await stat(absPath);
63
+ }
64
+ catch (error) {
65
+ if (!isMissing(error)) {
66
+ return { kind: "skipped", relPath, reason: `unreadable (${errnoCode(error) ?? errorMessage(error)})` };
67
+ }
68
+ }
69
+ if (source === undefined || !source.isFile()) {
70
+ const removed = await removeSidecar(workspaceRoot, relPath);
71
+ return removed ? { kind: "removed", relPath, sidecarPath } : { kind: "skipped", relPath, reason: "missing" };
72
+ }
73
+ if (source.size > MAX_SOURCE_BYTES) {
74
+ return { kind: "skipped", relPath, reason: `too-large (${Math.round(source.size / 1024 / 1024)} MB)` };
75
+ }
76
+ const format = await detectFormat(absPath);
77
+ if (format === undefined) {
78
+ return { kind: "skipped", relPath, reason: "unsupported" };
79
+ }
80
+ const deriver = DERIVERS[format];
81
+ const stamp = deriverStamp(deriver);
82
+ const sourceSha = await sha256OfFile(absPath);
83
+ const existing = await readSidecar(sidecarPath);
84
+ if (isFresh(existing, sourceSha, stamp)) {
85
+ const body = sidecarBody(existing ?? "");
86
+ return { kind: "fresh", relPath, format, sidecarPath, body, tokens: estimateTokens(body) };
87
+ }
88
+ let doc;
89
+ try {
90
+ doc = neutralizeDoc(await deriver.derive(absPath));
91
+ }
92
+ catch (error) {
93
+ const detail = errorMessage(error).split("\n")[0];
94
+ return { kind: "skipped", relPath, reason: `derive-failed (${format}): ${detail}` };
95
+ }
96
+ const written = await writeSidecar(workspaceRoot, { relPath, sourceSha, deriverStamp: stamp, doc, derivedAt: now() });
97
+ return { kind: "derived", relPath, format, sidecarPath: written.path, body: written.body, doc, tokens: written.tokens };
98
+ };
99
+ //# sourceMappingURL=derive.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"derive.js","sourceRoot":"","sources":["../../src/lib/derive.ts"],"names":[],"mappings":"AACA,OAAO,EAAE,IAAI,EAAE,MAAM,kBAAkB,CAAC;AACxC,OAAO,EAAE,UAAU,EAAE,QAAQ,EAAE,GAAG,EAAE,MAAM,WAAW,CAAC;AACtD,OAAO,EAAE,cAAc,EAAE,MAAM,uBAAuB,CAAC;AACvD,OAAO,EAAE,SAAS,EAAE,YAAY,EAAE,SAAS,EAAE,MAAM,uBAAuB,CAAC;AAC3E,OAAO,EAAE,YAAY,EAAE,mBAAmB,EAAE,eAAe,EAAE,MAAM,4BAA4B,CAAC;AAChG,OAAO,EAAE,SAAS,EAAE,MAAM,qBAAqB,CAAC;AAChD,OAAO,EAAE,YAAY,EAAe,MAAM,cAAc,CAAC;AACzD,OAAO,EAAE,YAAY,EAAE,aAAa,EAAiC,MAAM,uBAAuB,CAAC;AACnG,OAAO,EAAE,cAAc,EAAE,MAAM,uBAAuB,CAAC;AACvD,OAAO,EAAE,WAAW,EAAE,MAAM,oBAAoB,CAAC;AACjD,OAAO,EAAE,WAAW,EAAE,MAAM,oBAAoB,CAAC;AACjD,OAAO,EAAE,WAAW,EAAE,MAAM,oBAAoB,CAAC;AACjD,OAAO,EAAE,YAAY,EAAE,MAAM,qBAAqB,CAAC;AACnD,OAAO,EAAE,YAAY,EAAE,MAAM,qBAAqB,CAAC;AACnD,OAAO,EAAE,YAAY,EAAE,MAAM,qBAAqB,CAAC;AACnD,OAAO,EAAE,UAAU,EAAE,MAAM,mBAAmB,CAAC;AAC/C,OAAO,EAAE,UAAU,EAAE,MAAM,mBAAmB,CAAC;AAC/C,OAAO,EAAE,UAAU,EAAE,MAAM,mBAAmB,CAAC;AAC/C,OAAO,EAAE,UAAU,EAAE,MAAM,mBAAmB,CAAC;AAC/C,OAAO,EAAE,WAAW,EAAE,MAAM,oBAAoB,CAAC;AACjD,OAAO,EAAE,cAAc,EAAE,MAAM,uBAAuB,CAAC;AACvD,OAAO,EAAE,UAAU,EAAE,MAAM,mBAAmB,CAAC;AAC/C,OAAO,EAAE,WAAW,EAAE,MAAM,oBAAoB,CAAC;AACjD,OAAO,EAAE,OAAO,EAAE,WAAW,EAAE,aAAa,EAAE,WAAW,EAAE,cAAc,EAAE,YAAY,EAAE,YAAY,EAAE,MAAM,cAAc,CAAC;AAK5H,MAAM,CAAC,MAAM,QAAQ,GAA4B;IAC7C,IAAI,EAAE,WAAW;IACjB,IAAI,EAAE,WAAW;IACjB,IAAI,EAAE,WAAW;IACjB,GAAG,EAAE,UAAU;IACf,KAAK,EAAE,YAAY;IACnB,KAAK,EAAE,YAAY;IACnB,IAAI,EAAE,WAAW;IACjB,KAAK,EAAE,YAAY;IACnB,GAAG,EAAE,UAAU;IACf,GAAG,EAAE,UAAU;IACf,GAAG,EAAE,UAAU;IACf,GAAG,EAAE,UAAU;IACf,IAAI,EAAE,WAAW;IACjB,OAAO,EAAE,cAAc;IACvB,OAAO,EAAE,cAAc;CAC1B,CAAC;AAGF,MAAM,CAAC,MAAM,gBAAgB,GAAG,GAAG,GAAG,IAAI,GAAG,IAAI,CAAC;AAGlD,MAAM,CAAC,MAAM,SAAS,GAAG,CAAC,IAAY,EAAE,GAAW,EAAsB,EAAE;IACvE,MAAM,GAAG,GAAG,QAAQ,CAAC,IAAI,EAAE,GAAG,CAAC,CAAC;IAChC,OAAO,GAAG,KAAK,EAAE,IAAI,GAAG,CAAC,UAAU,CAAC,IAAI,CAAC,IAAI,UAAU,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,GAAG,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;AACxG,CAAC,CAAC;AAGF,MAAM,CAAC,MAAM,eAAe,GAAG,CAAC,OAAe,EAAW,EAAE;IACxD,MAAM,QAAQ,GAAG,OAAO,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC;IACpC,OAAO,QAAQ,CAAC,IAAI,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,YAAY,CAAC,GAAG,CAAC,OAAO,CAAC,IAAI,OAAO,KAAK,SAAS,CAAC,IAAI,eAAe,CAAC,OAAO,CAAC,IAAI,mBAAmB,CAAC,OAAO,CAAC,CAAC;AACtJ,CAAC,CAAC;AAwBF,MAAM,CAAC,MAAM,aAAa,GAAG,KAAK,EAAE,aAAqB,EAAE,OAAe,EAAE,GAAG,GAAe,GAAG,EAAE,CAAC,IAAI,IAAI,EAAE,EAAoB,EAAE;IAChI,MAAM,OAAO,GAAG,SAAS,CAAC,aAAa,EAAE,OAAO,CAAC,CAAC;IAClD,IAAI,OAAO,KAAK,SAAS,EAAE,CAAC;QACxB,OAAO,EAAE,IAAI,EAAE,SAAS,EAAE,OAAO,EAAE,OAAO,EAAE,MAAM,EAAE,mBAAmB,EAAE,CAAC;IAC9E,CAAC;IACD,IAAI,eAAe,CAAC,OAAO,CAAC,EAAE,CAAC;QAC3B,OAAO,EAAE,IAAI,EAAE,SAAS,EAAE,OAAO,EAAE,MAAM,EAAE,cAAc,EAAE,CAAC;IAChE,CAAC;IACD,MAAM,WAAW,GAAG,cAAc,CAAC,aAAa,EAAE,OAAO,CAAC,CAAC;IAC3D,IAAI,MAAyB,CAAC;IAC9B,IAAI,CAAC;QACD,MAAM,GAAG,MAAM,IAAI,CAAC,OAAO,CAAC,CAAC;IACjC,CAAC;IAAC,OAAO,KAAK,EAAE,CAAC;QAEb,IAAI,CAAC,SAAS,CAAC,KAAK,CAAC,EAAE,CAAC;YACpB,OAAO,EAAE,IAAI,EAAE,SAAS,EAAE,OAAO,EAAE,MAAM,EAAE,eAAe,SAAS,CAAC,KAAK,CAAC,IAAI,YAAY,CAAC,KAAK,CAAC,GAAG,EAAE,CAAC;QAC3G,CAAC;IACL,CAAC;IACD,IAAI,MAAM,KAAK,SAAS,IAAI,CAAC,MAAM,CAAC,MAAM,EAAE,EAAE,CAAC;QAC3C,MAAM,OAAO,GAAG,MAAM,aAAa,CAAC,aAAa,EAAE,OAAO,CAAC,CAAC;QAC5D,OAAO,OAAO,CAAC,CAAC,CAAC,EAAE,IAAI,EAAE,SAAS,EAAE,OAAO,EAAE,WAAW,EAAE,CAAC,CAAC,CAAC,EAAE,IAAI,EAAE,SAAS,EAAE,OAAO,EAAE,MAAM,EAAE,SAAS,EAAE,CAAC;IACjH,CAAC;IACD,IAAI,MAAM,CAAC,IAAI,GAAG,gBAAgB,EAAE,CAAC;QACjC,OAAO,EAAE,IAAI,EAAE,SAAS,EAAE,OAAO,EAAE,MAAM,EAAE,cAAc,IAAI,CAAC,KAAK,CAAC,MAAM,CAAC,IAAI,GAAG,IAAI,GAAG,IAAI,CAAC,MAAM,EAAE,CAAC;IAC3G,CAAC;IACD,MAAM,MAAM,GAAG,MAAM,YAAY,CAAC,OAAO,CAAC,CAAC;IAC3C,IAAI,MAAM,KAAK,SAAS,EAAE,CAAC;QACvB,OAAO,EAAE,IAAI,EAAE,SAAS,EAAE,OAAO,EAAE,MAAM,EAAE,aAAa,EAAE,CAAC;IAC/D,CAAC;IACD,MAAM,OAAO,GAAG,QAAQ,CAAC,MAAM,CAAC,CAAC;IACjC,MAAM,KAAK,GAAG,YAAY,CAAC,OAAO,CAAC,CAAC;IACpC,MAAM,SAAS,GAAG,MAAM,YAAY,CAAC,OAAO,CAAC,CAAC;IAC9C,MAAM,QAAQ,GAAG,MAAM,WAAW,CAAC,WAAW,CAAC,CAAC;IAChD,IAAI,OAAO,CAAC,QAAQ,EAAE,SAAS,EAAE,KAAK,CAAC,EAAE,CAAC;QACtC,MAAM,IAAI,GAAG,WAAW,CAAC,QAAQ,IAAI,EAAE,CAAC,CAAC;QACzC,OAAO,EAAE,IAAI,EAAE,OAAO,EAAE,OAAO,EAAE,MAAM,EAAE,WAAW,EAAE,IAAI,EAAE,MAAM,EAAE,cAAc,CAAC,IAAI,CAAC,EAAE,CAAC;IAC/F,CAAC;IAED,IAAI,GAAe,CAAC;IACpB,IAAI,CAAC;QACD,GAAG,GAAG,aAAa,CAAC,MAAM,OAAO,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC,CAAC;IACvD,CAAC;IAAC,OAAO,KAAK,EAAE,CAAC;QACb,MAAM,MAAM,GAAG,YAAY,CAAC,KAAK,CAAC,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,CAAC;QAClD,OAAO,EAAE,IAAI,EAAE,SAAS,EAAE,OAAO,EAAE,MAAM,EAAE,kBAAkB,MAAM,MAAM,MAAM,EAAE,EAAE,CAAC;IACxF,CAAC;IACD,MAAM,OAAO,GAAG,MAAM,YAAY,CAAC,aAAa,EAAE,EAAE,OAAO,EAAE,SAAS,EAAE,YAAY,EAAE,KAAK,EAAE,GAAG,EAAE,SAAS,EAAE,GAAG,EAAE,EAAE,CAAC,CAAC;IACtH,OAAO,EAAE,IAAI,EAAE,SAAS,EAAE,OAAO,EAAE,MAAM,EAAE,WAAW,EAAE,OAAO,CAAC,IAAI,EAAE,IAAI,EAAE,OAAO,CAAC,IAAI,EAAE,GAAG,EAAE,MAAM,EAAE,OAAO,CAAC,MAAM,EAAE,CAAC;AAC5H,CAAC,CAAC"}
@@ -0,0 +1,3 @@
1
+ import type { Deriver } from "./deriver.js";
2
+ export declare const archiveDeriver: Deriver;
3
+ //# sourceMappingURL=archive.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"archive.d.ts","sourceRoot":"","sources":["../../../src/lib/derivers/archive.ts"],"names":[],"mappings":"AAKA,OAAO,KAAK,EAAc,OAAO,EAAE,MAAM,cAAc,CAAC;AA0IxD,eAAO,MAAM,cAAc,EAAE,OAwB5B,CAAC"}
@@ -0,0 +1,132 @@
1
+ import { readFile } from "node:fs/promises";
2
+ import { basename } from "node:path";
3
+ import { gunzipSync } from "fflate";
4
+ import { plural } from "@intentic/base/format";
5
+ import { gzipHead, listWithTar, looksLikeTar, tarEntries, tarOnPath, zipEntries } from "../archives.js";
6
+ const MAX_ENTRIES = 500;
7
+ const MAX_UNPACKED_BYTES = 128 * 1024 * 1024;
8
+ const MAX_MEMBER_TEXT_BYTES = 256 * 1024;
9
+ const MAGIC = [
10
+ ["zip", [0x50, 0x4b]],
11
+ ["gzip", [0x1f, 0x8b]],
12
+ ["xz", [0xfd, 0x37, 0x7a, 0x58, 0x5a]],
13
+ ["bzip2", [0x42, 0x5a, 0x68]],
14
+ ["zstd", [0x28, 0xb5, 0x2f, 0xfd]],
15
+ ["7z", [0x37, 0x7a, 0xbc, 0xaf, 0x27, 0x1c]],
16
+ ["rar", [0x52, 0x61, 0x72, 0x21]],
17
+ ];
18
+ const containerOf = (bytes) => {
19
+ const magic = MAGIC.find(([, signature]) => signature.every((byte, index) => bytes[index] === byte));
20
+ return magic?.[0] ?? (looksLikeTar(bytes) ? "tar" : undefined);
21
+ };
22
+ const formatBytes = (bytes) => {
23
+ const units = ["B", "kB", "MB", "GB", "TB"];
24
+ let value = bytes;
25
+ let unit = 0;
26
+ while (value >= 1000 && unit < units.length - 1) {
27
+ value /= 1000;
28
+ unit += 1;
29
+ }
30
+ return `${unit === 0 ? value : value.toFixed(value < 10 ? 1 : 0)} ${units[unit]}`;
31
+ };
32
+ const summaryOf = (container, entries) => {
33
+ const files = entries.filter((entry) => !entry.directory);
34
+ const unpacked = files.reduce((sum, entry) => sum + (entry.size ?? 0), 0);
35
+ const packed = files.reduce((sum, entry) => sum + (entry.packed ?? 0), 0);
36
+ const folders = entries.length - files.length;
37
+ const lines = [`- Archive: ${container}`, `- Members: ${plural(files.length, "file")}${folders === 0 ? "" : `, ${plural(folders, "folder")}`}`];
38
+ const ratio = packed > 0 && unpacked > 0 ? ` · packed ${formatBytes(packed)} (${Math.round((1 - packed / unpacked) * 100)}% smaller)` : "";
39
+ if (unpacked > 0) {
40
+ lines.push(`- Unpacked: ${formatBytes(unpacked)}${ratio}`);
41
+ }
42
+ return lines;
43
+ };
44
+ const tableRow = (cells) => `| ${cells.map((cell) => cell.replaceAll("|", "\\|")).join(" | ")} |`;
45
+ const entryTable = (entries) => {
46
+ const files = entries.filter((entry) => !entry.directory).slice(0, MAX_ENTRIES);
47
+ if (files.length === 0) {
48
+ return "";
49
+ }
50
+ return [
51
+ tableRow(["Path", "Size"]),
52
+ tableRow(["---", "---"]),
53
+ ...files.map((entry) => tableRow([entry.path, entry.size === undefined ? "" : formatBytes(entry.size)])),
54
+ ].join("\n");
55
+ };
56
+ const listingDoc = (container, entries, notes) => {
57
+ const files = entries.filter((entry) => !entry.directory).length;
58
+ const table = entryTable(entries);
59
+ return {
60
+ markdown: [summaryOf(container, entries).join("\n"), table].filter((part) => part !== "").join("\n\n"),
61
+ notes: [
62
+ ...notes,
63
+ ...(files > MAX_ENTRIES ? [`listing ${MAX_ENTRIES} of ${files} files: the rest are in the archive, not here`] : []),
64
+ ...(entries.length === 0 ? ["this archive holds nothing"] : []),
65
+ "member listing only: what the files inside SAY is not derived — unpack the archive to read them",
66
+ ],
67
+ };
68
+ };
69
+ const isText = (bytes) => !bytes.subarray(0, 8192).includes(0);
70
+ const memberDoc = (name, unpacked) => {
71
+ const facts = [`- Archive: gzip`, `- Member: ${name}`, `- Unpacked: ${formatBytes(unpacked.length)}`].join("\n");
72
+ if (!isText(unpacked)) {
73
+ return { markdown: facts, notes: [`${name} is not text: nothing inside this archive can be shown as prose`] };
74
+ }
75
+ const clipped = unpacked.length > MAX_MEMBER_TEXT_BYTES;
76
+ const text = new TextDecoder().decode(unpacked.subarray(0, MAX_MEMBER_TEXT_BYTES));
77
+ return {
78
+ markdown: `${facts}\n\n## ${name}\n\n${clipped ? text.slice(0, text.lastIndexOf("\n") + 1) : text}`,
79
+ notes: clipped ? [`showing the first ${formatBytes(MAX_MEMBER_TEXT_BYTES)} of ${formatBytes(unpacked.length)}: the rest is in the archive`] : [],
80
+ };
81
+ };
82
+ const gzipDoc = (absPath, bytes) => {
83
+ const head = gzipHead(bytes);
84
+ const name = head?.name ?? basename(absPath).replace(/\.(gz|tgz)$/i, "");
85
+ if (head !== undefined && head.unpackedBytes > MAX_UNPACKED_BYTES) {
86
+ return {
87
+ markdown: [`- Archive: gzip`, `- Member: ${name}`, `- Unpacked: ${formatBytes(head.unpackedBytes)}`].join("\n"),
88
+ notes: [`too large to open in the background (${formatBytes(head.unpackedBytes)} unpacked): the header's facts are all this shadow carries`],
89
+ };
90
+ }
91
+ const unpacked = gunzipSync(bytes);
92
+ return looksLikeTar(unpacked) ? listingDoc("gzip", tarEntries(unpacked), ["gzip-compressed tar"]) : memberDoc(name, unpacked);
93
+ };
94
+ const externalDoc = async (container, absPath) => {
95
+ if (!tarOnPath()) {
96
+ return { markdown: `- Archive: ${container}`, notes: [`no listing: reading a ${container} archive needs tar, which is not on PATH here`] };
97
+ }
98
+ try {
99
+ return listingDoc(container, await listWithTar(absPath), [`listed through tar`]);
100
+ }
101
+ catch {
102
+ return {
103
+ markdown: `- Archive: ${container}`,
104
+ notes: [`no listing: this is a single ${container}-compressed file rather than an archive, and ${container} is not decompressed by this tier`],
105
+ };
106
+ }
107
+ };
108
+ const UNREADABLE = new Set(["7z", "rar"]);
109
+ export const archiveDeriver = {
110
+ get name() {
111
+ return tarOnPath() ? "archive+tar" : "archive";
112
+ },
113
+ version: 1,
114
+ derive: async (absPath) => {
115
+ const bytes = new Uint8Array(await readFile(absPath));
116
+ const container = containerOf(bytes);
117
+ if (container === undefined) {
118
+ throw new Error("not an archive: no container signature in the first bytes");
119
+ }
120
+ if (UNREADABLE.has(container)) {
121
+ return { markdown: `- Archive: ${container}`, notes: [`no listing: nothing in this image opens a ${container} archive`] };
122
+ }
123
+ if (container === "zip") {
124
+ return listingDoc(container, zipEntries(bytes), []);
125
+ }
126
+ if (container === "tar") {
127
+ return listingDoc(container, tarEntries(bytes), []);
128
+ }
129
+ return container === "gzip" ? gzipDoc(absPath, bytes) : externalDoc(container, absPath);
130
+ },
131
+ };
132
+ //# sourceMappingURL=archive.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"archive.js","sourceRoot":"","sources":["../../../src/lib/derivers/archive.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,EAAE,MAAM,kBAAkB,CAAC;AAC5C,OAAO,EAAE,QAAQ,EAAE,MAAM,WAAW,CAAC;AACrC,OAAO,EAAE,UAAU,EAAE,MAAM,QAAQ,CAAC;AACpC,OAAO,EAAE,MAAM,EAAE,MAAM,uBAAuB,CAAC;AAC/C,OAAO,EAAE,QAAQ,EAAE,WAAW,EAAE,YAAY,EAAE,UAAU,EAAE,SAAS,EAAE,UAAU,EAAqB,MAAM,gBAAgB,CAAC;AAM3H,MAAM,WAAW,GAAG,GAAG,CAAC;AAExB,MAAM,kBAAkB,GAAG,GAAG,GAAG,IAAI,GAAG,IAAI,CAAC;AAE7C,MAAM,qBAAqB,GAAG,GAAG,GAAG,IAAI,CAAC;AAMzC,MAAM,KAAK,GAAyD;IAChE,CAAC,KAAK,EAAE,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC;IACrB,CAAC,MAAM,EAAE,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC;IACtB,CAAC,IAAI,EAAE,CAAC,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,CAAC,CAAC;IACtC,CAAC,OAAO,EAAE,CAAC,IAAI,EAAE,IAAI,EAAE,IAAI,CAAC,CAAC;IAC7B,CAAC,MAAM,EAAE,CAAC,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,CAAC,CAAC;IAClC,CAAC,IAAI,EAAE,CAAC,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,CAAC,CAAC;IAC5C,CAAC,KAAK,EAAE,CAAC,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,CAAC,CAAC;CACpC,CAAC;AAEF,MAAM,WAAW,GAAG,CAAC,KAAiB,EAAyB,EAAE;IAC7D,MAAM,KAAK,GAAG,KAAK,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,SAAS,CAAC,EAAE,EAAE,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC,IAAI,EAAE,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,KAAK,CAAC,KAAK,IAAI,CAAC,CAAC,CAAC;IACrG,OAAO,KAAK,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,YAAY,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC;AACnE,CAAC,CAAC;AAIF,MAAM,WAAW,GAAG,CAAC,KAAa,EAAU,EAAE;IAC1C,MAAM,KAAK,GAAG,CAAC,GAAG,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,CAAC,CAAC;IAC5C,IAAI,KAAK,GAAG,KAAK,CAAC;IAClB,IAAI,IAAI,GAAG,CAAC,CAAC;IACb,OAAO,KAAK,IAAI,IAAI,IAAI,IAAI,GAAG,KAAK,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QAC9C,KAAK,IAAI,IAAI,CAAC;QACd,IAAI,IAAI,CAAC,CAAC;IACd,CAAC;IACD,OAAO,GAAG,IAAI,KAAK,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,OAAO,CAAC,KAAK,GAAG,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,IAAI,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC;AACtF,CAAC,CAAC;AAGF,MAAM,SAAS,GAAG,CAAC,SAAoB,EAAE,OAAgC,EAAY,EAAE;IACnF,MAAM,KAAK,GAAG,OAAO,CAAC,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC,KAAK,CAAC,SAAS,CAAC,CAAC;IAC1D,MAAM,QAAQ,GAAG,KAAK,CAAC,MAAM,CAAC,CAAC,GAAG,EAAE,KAAK,EAAE,EAAE,CAAC,GAAG,GAAG,CAAC,KAAK,CAAC,IAAI,IAAI,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC;IAC1E,MAAM,MAAM,GAAG,KAAK,CAAC,MAAM,CAAC,CAAC,GAAG,EAAE,KAAK,EAAE,EAAE,CAAC,GAAG,GAAG,CAAC,KAAK,CAAC,MAAM,IAAI,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC;IAC1E,MAAM,OAAO,GAAG,OAAO,CAAC,MAAM,GAAG,KAAK,CAAC,MAAM,CAAC;IAC9C,MAAM,KAAK,GAAG,CAAC,cAAc,SAAS,EAAE,EAAE,cAAc,MAAM,CAAC,KAAK,CAAC,MAAM,EAAE,MAAM,CAAC,GAAG,OAAO,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,KAAK,MAAM,CAAC,OAAO,EAAE,QAAQ,CAAC,EAAE,EAAE,CAAC,CAAC;IAEhJ,MAAM,KAAK,GAAG,MAAM,GAAG,CAAC,IAAI,QAAQ,GAAG,CAAC,CAAC,CAAC,CAAC,aAAa,WAAW,CAAC,MAAM,CAAC,KAAK,IAAI,CAAC,KAAK,CAAC,CAAC,CAAC,GAAG,MAAM,GAAG,QAAQ,CAAC,GAAG,GAAG,CAAC,YAAY,CAAC,CAAC,CAAC,EAAE,CAAC;IAC3I,IAAI,QAAQ,GAAG,CAAC,EAAE,CAAC;QACf,KAAK,CAAC,IAAI,CAAC,eAAe,WAAW,CAAC,QAAQ,CAAC,GAAG,KAAK,EAAE,CAAC,CAAC;IAC/D,CAAC;IACD,OAAO,KAAK,CAAC;AACjB,CAAC,CAAC;AAEF,MAAM,QAAQ,GAAG,CAAC,KAAwB,EAAU,EAAE,CAAC,KAAK,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,UAAU,CAAC,GAAG,EAAE,KAAK,CAAC,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC;AAG7H,MAAM,UAAU,GAAG,CAAC,OAAgC,EAAU,EAAE;IAC5D,MAAM,KAAK,GAAG,OAAO,CAAC,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC,KAAK,CAAC,SAAS,CAAC,CAAC,KAAK,CAAC,CAAC,EAAE,WAAW,CAAC,CAAC;IAChF,IAAI,KAAK,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QACrB,OAAO,EAAE,CAAC;IACd,CAAC;IACD,OAAO;QACH,QAAQ,CAAC,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;QAC1B,QAAQ,CAAC,CAAC,KAAK,EAAE,KAAK,CAAC,CAAC;QACxB,GAAG,KAAK,CAAC,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,QAAQ,CAAC,CAAC,KAAK,CAAC,IAAI,EAAE,KAAK,CAAC,IAAI,KAAK,SAAS,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,WAAW,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;KAC3G,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;AACjB,CAAC,CAAC;AAEF,MAAM,UAAU,GAAG,CAAC,SAAoB,EAAE,OAAgC,EAAE,KAAwB,EAAc,EAAE;IAChH,MAAM,KAAK,GAAG,OAAO,CAAC,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC,KAAK,CAAC,SAAS,CAAC,CAAC,MAAM,CAAC;IACjE,MAAM,KAAK,GAAG,UAAU,CAAC,OAAO,CAAC,CAAC;IAClC,OAAO;QACH,QAAQ,EAAE,CAAC,SAAS,CAAC,SAAS,EAAE,OAAO,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,KAAK,CAAC,CAAC,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,KAAK,EAAE,CAAC,CAAC,IAAI,CAAC,MAAM,CAAC;QACtG,KAAK,EAAE;YACH,GAAG,KAAK;YACR,GAAG,CAAC,KAAK,GAAG,WAAW,CAAC,CAAC,CAAC,CAAC,WAAW,WAAW,OAAO,KAAK,+CAA+C,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;YACnH,GAAG,CAAC,OAAO,CAAC,MAAM,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,4BAA4B,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;YAC/D,iGAAiG;SACpG;KACJ,CAAC;AACN,CAAC,CAAC;AAGF,MAAM,MAAM,GAAG,CAAC,KAAiB,EAAW,EAAE,CAAC,CAAC,KAAK,CAAC,QAAQ,CAAC,CAAC,EAAE,IAAI,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC;AAGpF,MAAM,SAAS,GAAG,CAAC,IAAY,EAAE,QAAoB,EAAc,EAAE;IACjE,MAAM,KAAK,GAAG,CAAC,iBAAiB,EAAE,aAAa,IAAI,EAAE,EAAE,eAAe,WAAW,CAAC,QAAQ,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IACjH,IAAI,CAAC,MAAM,CAAC,QAAQ,CAAC,EAAE,CAAC;QACpB,OAAO,EAAE,QAAQ,EAAE,KAAK,EAAE,KAAK,EAAE,CAAC,GAAG,IAAI,iEAAiE,CAAC,EAAE,CAAC;IAClH,CAAC;IACD,MAAM,OAAO,GAAG,QAAQ,CAAC,MAAM,GAAG,qBAAqB,CAAC;IACxD,MAAM,IAAI,GAAG,IAAI,WAAW,EAAE,CAAC,MAAM,CAAC,QAAQ,CAAC,QAAQ,CAAC,CAAC,EAAE,qBAAqB,CAAC,CAAC,CAAC;IACnF,OAAO;QACH,QAAQ,EAAE,GAAG,KAAK,UAAU,IAAI,OAAO,OAAO,CAAC,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,EAAE,IAAI,CAAC,WAAW,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,IAAI,EAAE;QACnG,KAAK,EAAE,OAAO,CAAC,CAAC,CAAC,CAAC,qBAAqB,WAAW,CAAC,qBAAqB,CAAC,OAAO,WAAW,CAAC,QAAQ,CAAC,MAAM,CAAC,8BAA8B,CAAC,CAAC,CAAC,CAAC,EAAE;KACnJ,CAAC;AACN,CAAC,CAAC;AAEF,MAAM,OAAO,GAAG,CAAC,OAAe,EAAE,KAAiB,EAAc,EAAE;IAC/D,MAAM,IAAI,GAAG,QAAQ,CAAC,KAAK,CAAC,CAAC;IAC7B,MAAM,IAAI,GAAG,IAAI,EAAE,IAAI,IAAI,QAAQ,CAAC,OAAO,CAAC,CAAC,OAAO,CAAC,cAAc,EAAE,EAAE,CAAC,CAAC;IACzE,IAAI,IAAI,KAAK,SAAS,IAAI,IAAI,CAAC,aAAa,GAAG,kBAAkB,EAAE,CAAC;QAChE,OAAO;YACH,QAAQ,EAAE,CAAC,iBAAiB,EAAE,aAAa,IAAI,EAAE,EAAE,eAAe,WAAW,CAAC,IAAI,CAAC,aAAa,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC;YAC/G,KAAK,EAAE,CAAC,wCAAwC,WAAW,CAAC,IAAI,CAAC,aAAa,CAAC,4DAA4D,CAAC;SAC/I,CAAC;IACN,CAAC;IACD,MAAM,QAAQ,GAAG,UAAU,CAAC,KAAK,CAAC,CAAC;IAEnC,OAAO,YAAY,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,UAAU,CAAC,MAAM,EAAE,UAAU,CAAC,QAAQ,CAAC,EAAE,CAAC,qBAAqB,CAAC,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC,IAAI,EAAE,QAAQ,CAAC,CAAC;AAClI,CAAC,CAAC;AAGF,MAAM,WAAW,GAAG,KAAK,EAAE,SAAoB,EAAE,OAAe,EAAuB,EAAE;IACrF,IAAI,CAAC,SAAS,EAAE,EAAE,CAAC;QACf,OAAO,EAAE,QAAQ,EAAE,cAAc,SAAS,EAAE,EAAE,KAAK,EAAE,CAAC,yBAAyB,SAAS,+CAA+C,CAAC,EAAE,CAAC;IAC/I,CAAC;IACD,IAAI,CAAC;QACD,OAAO,UAAU,CAAC,SAAS,EAAE,MAAM,WAAW,CAAC,OAAO,CAAC,EAAE,CAAC,oBAAoB,CAAC,CAAC,CAAC;IACrF,CAAC;IAAC,MAAM,CAAC;QAGL,OAAO;YACH,QAAQ,EAAE,cAAc,SAAS,EAAE;YACnC,KAAK,EAAE,CAAC,gCAAgC,SAAS,gDAAgD,SAAS,mCAAmC,CAAC;SACjJ,CAAC;IACN,CAAC;AACL,CAAC,CAAC;AAGF,MAAM,UAAU,GAA2B,IAAI,GAAG,CAAC,CAAC,IAAI,EAAE,KAAK,CAAC,CAAC,CAAC;AAElE,MAAM,CAAC,MAAM,cAAc,GAAY;IAGnC,IAAI,IAAI;QACJ,OAAO,SAAS,EAAE,CAAC,CAAC,CAAC,aAAa,CAAC,CAAC,CAAC,SAAS,CAAC;IACnD,CAAC;IACD,OAAO,EAAE,CAAC;IACV,MAAM,EAAE,KAAK,EAAE,OAAO,EAAuB,EAAE;QAC3C,MAAM,KAAK,GAAG,IAAI,UAAU,CAAC,MAAM,QAAQ,CAAC,OAAO,CAAC,CAAC,CAAC;QACtD,MAAM,SAAS,GAAG,WAAW,CAAC,KAAK,CAAC,CAAC;QACrC,IAAI,SAAS,KAAK,SAAS,EAAE,CAAC;YAC1B,MAAM,IAAI,KAAK,CAAC,2DAA2D,CAAC,CAAC;QACjF,CAAC;QACD,IAAI,UAAU,CAAC,GAAG,CAAC,SAAS,CAAC,EAAE,CAAC;YAC5B,OAAO,EAAE,QAAQ,EAAE,cAAc,SAAS,EAAE,EAAE,KAAK,EAAE,CAAC,6CAA6C,SAAS,UAAU,CAAC,EAAE,CAAC;QAC9H,CAAC;QACD,IAAI,SAAS,KAAK,KAAK,EAAE,CAAC;YACtB,OAAO,UAAU,CAAC,SAAS,EAAE,UAAU,CAAC,KAAK,CAAC,EAAE,EAAE,CAAC,CAAC;QACxD,CAAC;QACD,IAAI,SAAS,KAAK,KAAK,EAAE,CAAC;YACtB,OAAO,UAAU,CAAC,SAAS,EAAE,UAAU,CAAC,KAAK,CAAC,EAAE,EAAE,CAAC,CAAC;QACxD,CAAC;QACD,OAAO,SAAS,KAAK,MAAM,CAAC,CAAC,CAAC,OAAO,CAAC,OAAO,EAAE,KAAK,CAAC,CAAC,CAAC,CAAC,WAAW,CAAC,SAAS,EAAE,OAAO,CAAC,CAAC;IAC5F,CAAC;CACJ,CAAC"}
@@ -0,0 +1,13 @@
1
+ export interface DerivedDoc {
2
+ readonly markdown: string;
3
+ readonly title?: string | undefined;
4
+ readonly notes: string[];
5
+ }
6
+ export interface Deriver {
7
+ readonly name: string;
8
+ readonly version: number;
9
+ readonly derive: (absPath: string) => Promise<DerivedDoc>;
10
+ }
11
+ export declare const deriverStamp: (deriver: Deriver) => string;
12
+ export declare const neutralizeDoc: (doc: DerivedDoc) => DerivedDoc;
13
+ //# sourceMappingURL=deriver.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"deriver.d.ts","sourceRoot":"","sources":["../../../src/lib/derivers/deriver.ts"],"names":[],"mappings":"AAOA,MAAM,WAAW,UAAU;IAEvB,QAAQ,CAAC,QAAQ,EAAE,MAAM,CAAC;IAE1B,QAAQ,CAAC,KAAK,CAAC,EAAE,MAAM,GAAG,SAAS,CAAC;IAEpC,QAAQ,CAAC,KAAK,EAAE,MAAM,EAAE,CAAC;CAC5B;AAED,MAAM,WAAW,OAAO;IACpB,QAAQ,CAAC,IAAI,EAAE,MAAM,CAAC;IACtB,QAAQ,CAAC,OAAO,EAAE,MAAM,CAAC;IACzB,QAAQ,CAAC,MAAM,EAAE,CAAC,OAAO,EAAE,MAAM,KAAK,OAAO,CAAC,UAAU,CAAC,CAAC;CAC7D;AAGD,eAAO,MAAM,YAAY,YAAa,OAAO,KAAG,MAA+C,CAAC;AAKhG,eAAO,MAAM,aAAa,QAAS,UAAU,KAAG,UAI9C,CAAC"}
@@ -0,0 +1,8 @@
1
+ import { neutralizeOutsideText } from "@intentic/base/outside-text";
2
+ export const deriverStamp = (deriver) => `${deriver.name} v${deriver.version}`;
3
+ export const neutralizeDoc = (doc) => ({
4
+ markdown: neutralizeOutsideText(doc.markdown),
5
+ title: doc.title === undefined ? undefined : neutralizeOutsideText(doc.title),
6
+ notes: doc.notes.map((note) => neutralizeOutsideText(note)),
7
+ });
8
+ //# sourceMappingURL=deriver.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"deriver.js","sourceRoot":"","sources":["../../../src/lib/derivers/deriver.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,qBAAqB,EAAE,MAAM,6BAA6B,CAAC;AAuBpE,MAAM,CAAC,MAAM,YAAY,GAAG,CAAC,OAAgB,EAAU,EAAE,CAAC,GAAG,OAAO,CAAC,IAAI,KAAK,OAAO,CAAC,OAAO,EAAE,CAAC;AAKhG,MAAM,CAAC,MAAM,aAAa,GAAG,CAAC,GAAe,EAAc,EAAE,CAAC,CAAC;IAC3D,QAAQ,EAAE,qBAAqB,CAAC,GAAG,CAAC,QAAQ,CAAC;IAC7C,KAAK,EAAE,GAAG,CAAC,KAAK,KAAK,SAAS,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,qBAAqB,CAAC,GAAG,CAAC,KAAK,CAAC;IAC7E,KAAK,EAAE,GAAG,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,qBAAqB,CAAC,IAAI,CAAC,CAAC;CAC9D,CAAC,CAAC"}
@@ -0,0 +1,6 @@
1
+ import type { Deriver } from "./deriver.js";
2
+ export declare const notesOf: (messages: readonly {
3
+ readonly message: string;
4
+ }[]) => string[];
5
+ export declare const docxDeriver: Deriver;
6
+ //# sourceMappingURL=docx.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"docx.d.ts","sourceRoot":"","sources":["../../../src/lib/derivers/docx.ts"],"names":[],"mappings":"AAEA,OAAO,KAAK,EAAc,OAAO,EAAE,MAAM,cAAc,CAAC;AAgBxD,eAAO,MAAM,OAAO,aAAc,SAAS;IAAE,QAAQ,CAAC,OAAO,EAAE,MAAM,CAAA;CAAE,EAAE,KAAG,MAAM,EAajF,CAAC;AAEF,eAAO,MAAM,WAAW,EAAE,OAUzB,CAAC"}
@@ -0,0 +1,29 @@
1
+ import { bodyOf, parseHtml } from "@intentic/webq/dom";
2
+ import { renderMarkdown } from "@intentic/webq/markdown";
3
+ const STYLE_WARNING = /^Unrecognised (?:paragraph|run|table) style: '(.*)' \(Style ID: /;
4
+ const MAX_NOTES = 5;
5
+ export const notesOf = (messages) => {
6
+ const distinct = [...new Set(messages.map((message) => message.message))];
7
+ const styles = new Set(distinct.flatMap((warning) => STYLE_WARNING.exec(warning)?.[1] ?? []));
8
+ const others = distinct.filter((warning) => !STYLE_WARNING.test(warning));
9
+ const notes = others.slice(0, MAX_NOTES).map((warning) => `docx conversion: ${warning}`);
10
+ if (others.length > MAX_NOTES) {
11
+ notes.push(`docx conversion: ${others.length - MAX_NOTES} more warnings of the same kind`);
12
+ }
13
+ if (styles.size > 0) {
14
+ notes.push(`docx conversion: ${styles.size} Word style${styles.size === 1 ? "" : "s"} without a markdown equivalent, read as plain text`);
15
+ }
16
+ return notes;
17
+ };
18
+ export const docxDeriver = {
19
+ name: "docx",
20
+ version: 2,
21
+ derive: async (absPath) => {
22
+ const { default: mammoth } = await import("mammoth");
23
+ const converted = await mammoth.convertToHtml({ path: absPath });
24
+ const body = bodyOf(parseHtml(converted.value));
25
+ const markdown = body === undefined ? "" : renderMarkdown(body);
26
+ return { markdown, notes: notesOf(converted.messages) };
27
+ },
28
+ };
29
+ //# sourceMappingURL=docx.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"docx.js","sourceRoot":"","sources":["../../../src/lib/derivers/docx.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,MAAM,EAAE,SAAS,EAAE,MAAM,oBAAoB,CAAC;AACvD,OAAO,EAAE,cAAc,EAAE,MAAM,yBAAyB,CAAC;AAUzD,MAAM,aAAa,GAAG,kEAAkE,CAAC;AAIzF,MAAM,SAAS,GAAG,CAAC,CAAC;AAGpB,MAAM,CAAC,MAAM,OAAO,GAAG,CAAC,QAAiD,EAAY,EAAE;IACnF,MAAM,QAAQ,GAAG,CAAC,GAAG,IAAI,GAAG,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,OAAO,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC;IAE1E,MAAM,MAAM,GAAG,IAAI,GAAG,CAAC,QAAQ,CAAC,OAAO,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,aAAa,CAAC,IAAI,CAAC,OAAO,CAAC,EAAE,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC;IAC9F,MAAM,MAAM,GAAG,QAAQ,CAAC,MAAM,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,CAAC,aAAa,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC,CAAC;IAC1E,MAAM,KAAK,GAAG,MAAM,CAAC,KAAK,CAAC,CAAC,EAAE,SAAS,CAAC,CAAC,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,oBAAoB,OAAO,EAAE,CAAC,CAAC;IACzF,IAAI,MAAM,CAAC,MAAM,GAAG,SAAS,EAAE,CAAC;QAC5B,KAAK,CAAC,IAAI,CAAC,oBAAoB,MAAM,CAAC,MAAM,GAAG,SAAS,iCAAiC,CAAC,CAAC;IAC/F,CAAC;IACD,IAAI,MAAM,CAAC,IAAI,GAAG,CAAC,EAAE,CAAC;QAClB,KAAK,CAAC,IAAI,CAAC,oBAAoB,MAAM,CAAC,IAAI,cAAc,MAAM,CAAC,IAAI,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,GAAG,oDAAoD,CAAC,CAAC;IAC9I,CAAC;IACD,OAAO,KAAK,CAAC;AACjB,CAAC,CAAC;AAEF,MAAM,CAAC,MAAM,WAAW,GAAY;IAChC,IAAI,EAAE,MAAM;IACZ,OAAO,EAAE,CAAC;IACV,MAAM,EAAE,KAAK,EAAE,OAAO,EAAuB,EAAE;QAC3C,MAAM,EAAE,OAAO,EAAE,OAAO,EAAE,GAAG,MAAM,MAAM,CAAC,SAAS,CAAC,CAAC;QACrD,MAAM,SAAS,GAAG,MAAM,OAAO,CAAC,aAAa,CAAC,EAAE,IAAI,EAAE,OAAO,EAAE,CAAC,CAAC;QACjE,MAAM,IAAI,GAAG,MAAM,CAAC,SAAS,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC,CAAC;QAChD,MAAM,QAAQ,GAAG,IAAI,KAAK,SAAS,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,cAAc,CAAC,IAAI,CAAC,CAAC;QAChE,OAAO,EAAE,QAAQ,EAAE,KAAK,EAAE,OAAO,CAAC,SAAS,CAAC,QAAQ,CAAC,EAAE,CAAC;IAC5D,CAAC;CACJ,CAAC"}
@@ -0,0 +1,3 @@
1
+ import type { Deriver } from "./deriver.js";
2
+ export declare const epubDeriver: Deriver;
3
+ //# sourceMappingURL=epub.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"epub.d.ts","sourceRoot":"","sources":["../../../src/lib/derivers/epub.ts"],"names":[],"mappings":"AAKA,OAAO,KAAK,EAAc,OAAO,EAAE,MAAM,cAAc,CAAC;AA8FxD,eAAO,MAAM,WAAW,EAAE,OA8BzB,CAAC"}
@@ -0,0 +1,102 @@
1
+ import { readFile } from "node:fs/promises";
2
+ import { posix } from "node:path";
3
+ import { unzipSync } from "fflate";
4
+ import { bodyOf, metaOf, parseHtml } from "@intentic/webq/dom";
5
+ import { renderMarkdown } from "@intentic/webq/markdown";
6
+ import { attributeOf, decodeEntities } from "../xml.js";
7
+ const MAX_MARKDOWN_BYTES = 2 * 1024 * 1024;
8
+ const decoder = new TextDecoder();
9
+ const partOf = (zip, name) => (zip[name] === undefined ? undefined : decoder.decode(zip[name]));
10
+ const manifestOf = (opf) => {
11
+ const items = new Map();
12
+ for (const match of opf.matchAll(/<(?:opf:)?item\b([^>]*?)\/?>/g)) {
13
+ const attributes = match[1] ?? "";
14
+ const id = attributeOf(attributes, "id");
15
+ const href = attributeOf(attributes, "href");
16
+ if (id !== undefined && href !== undefined) {
17
+ items.set(id, {
18
+ href,
19
+ mediaType: attributeOf(attributes, "media-type") ?? "",
20
+ nav: (attributeOf(attributes, "properties") ?? "").split(/\s+/).includes("nav"),
21
+ });
22
+ }
23
+ }
24
+ return items;
25
+ };
26
+ const spineOf = (opf) => [...opf.matchAll(/<(?:opf:)?itemref\b([^>]*?)\/?>/g)]
27
+ .map((match) => attributeOf(match[1] ?? "", "idref"))
28
+ .filter((idref) => idref !== undefined);
29
+ const readPackage = (zip) => {
30
+ const container = partOf(zip, "META-INF/container.xml");
31
+ const opfPath = container === undefined ? undefined : /full-path\s*=\s*"([^"]+)"/.exec(container)?.[1];
32
+ const opf = opfPath === undefined ? undefined : partOf(zip, opfPath);
33
+ if (opfPath === undefined || opf === undefined) {
34
+ return undefined;
35
+ }
36
+ const titleMatch = /<dc:title[^>]*>([\s\S]*?)<\/dc:title>/.exec(opf);
37
+ const raw = titleMatch?.[1]?.trim() ?? "";
38
+ return { dir: posix.dirname(opfPath), title: raw === "" ? undefined : decodeEntities(raw), manifest: manifestOf(opf), spine: spineOf(opf) };
39
+ };
40
+ const chapterOf = (zip, pkg, idref) => {
41
+ const item = pkg.manifest.get(idref);
42
+ if (item === undefined || item.nav || !/x?html/.test(item.mediaType)) {
43
+ return undefined;
44
+ }
45
+ const path = posix.normalize(posix.join(pkg.dir, decodeURIComponent(item.href.split("#")[0] ?? item.href)));
46
+ const html = partOf(zip, path);
47
+ if (html === undefined) {
48
+ return "missing";
49
+ }
50
+ const doc = parseHtml(html);
51
+ const body = bodyOf(doc);
52
+ const markdown = body === undefined ? "" : renderMarkdown(body).trim();
53
+ if (markdown === "") {
54
+ return undefined;
55
+ }
56
+ return markdown.startsWith("#") ? markdown : `## ${metaOf(doc).title || posix.basename(path)}\n\n${markdown}`;
57
+ };
58
+ const notesOf = (rendered, chapters, missing, capped) => {
59
+ const notes = [];
60
+ if (capped) {
61
+ notes.push(`showing ${rendered} of ${chapters} chapters: cut at ${Math.round(MAX_MARKDOWN_BYTES / 1024 / 1024)} MB of text`);
62
+ }
63
+ if (missing > 0) {
64
+ notes.push(`${missing} spine item${missing === 1 ? "" : "s"} named in the package but absent from the archive`);
65
+ }
66
+ if (chapters === 0) {
67
+ notes.push("no readable chapters in this EPUB");
68
+ }
69
+ return notes;
70
+ };
71
+ export const epubDeriver = {
72
+ name: "epub",
73
+ version: 1,
74
+ derive: async (absPath) => {
75
+ const zip = unzipSync(new Uint8Array(await readFile(absPath)));
76
+ const pkg = readPackage(zip);
77
+ if (pkg === undefined) {
78
+ return { markdown: "", notes: ["no package document (OPF) found: META-INF/container.xml is missing or points nowhere"] };
79
+ }
80
+ const sections = [];
81
+ let bytes = 0;
82
+ let chapters = 0;
83
+ let missing = 0;
84
+ for (const idref of pkg.spine) {
85
+ const chapter = chapterOf(zip, pkg, idref);
86
+ if (chapter === undefined) {
87
+ continue;
88
+ }
89
+ if (chapter === "missing") {
90
+ missing += 1;
91
+ continue;
92
+ }
93
+ chapters += 1;
94
+ if (bytes < MAX_MARKDOWN_BYTES) {
95
+ sections.push(chapter);
96
+ bytes += chapter.length;
97
+ }
98
+ }
99
+ return { markdown: sections.join("\n\n"), title: pkg.title, notes: notesOf(sections.length, chapters, missing, bytes >= MAX_MARKDOWN_BYTES) };
100
+ },
101
+ };
102
+ //# sourceMappingURL=epub.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"epub.js","sourceRoot":"","sources":["../../../src/lib/derivers/epub.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,EAAE,MAAM,kBAAkB,CAAC;AAC5C,OAAO,EAAE,KAAK,EAAE,MAAM,WAAW,CAAC;AAClC,OAAO,EAAE,SAAS,EAAiB,MAAM,QAAQ,CAAC;AAClD,OAAO,EAAE,MAAM,EAAE,MAAM,EAAE,SAAS,EAAE,MAAM,oBAAoB,CAAC;AAC/D,OAAO,EAAE,cAAc,EAAE,MAAM,yBAAyB,CAAC;AAEzD,OAAO,EAAE,WAAW,EAAE,cAAc,EAAE,MAAM,WAAW,CAAC;AAIxD,MAAM,kBAAkB,GAAG,CAAC,GAAG,IAAI,GAAG,IAAI,CAAC;AAe3C,MAAM,OAAO,GAAG,IAAI,WAAW,EAAE,CAAC;AAElC,MAAM,MAAM,GAAG,CAAC,GAAa,EAAE,IAAY,EAAsB,EAAE,CAAC,CAAC,GAAG,CAAC,IAAI,CAAC,KAAK,SAAS,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,OAAO,CAAC,MAAM,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;AAEtI,MAAM,UAAU,GAAG,CAAC,GAAW,EAA6B,EAAE;IAC1D,MAAM,KAAK,GAAG,IAAI,GAAG,EAAwB,CAAC;IAC9C,KAAK,MAAM,KAAK,IAAI,GAAG,CAAC,QAAQ,CAAC,+BAA+B,CAAC,EAAE,CAAC;QAChE,MAAM,UAAU,GAAG,KAAK,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC;QAClC,MAAM,EAAE,GAAG,WAAW,CAAC,UAAU,EAAE,IAAI,CAAC,CAAC;QACzC,MAAM,IAAI,GAAG,WAAW,CAAC,UAAU,EAAE,MAAM,CAAC,CAAC;QAC7C,IAAI,EAAE,KAAK,SAAS,IAAI,IAAI,KAAK,SAAS,EAAE,CAAC;YACzC,KAAK,CAAC,GAAG,CAAC,EAAE,EAAE;gBACV,IAAI;gBACJ,SAAS,EAAE,WAAW,CAAC,UAAU,EAAE,YAAY,CAAC,IAAI,EAAE;gBACtD,GAAG,EAAE,CAAC,WAAW,CAAC,UAAU,EAAE,YAAY,CAAC,IAAI,EAAE,CAAC,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,QAAQ,CAAC,KAAK,CAAC;aAClF,CAAC,CAAC;QACP,CAAC;IACL,CAAC;IACD,OAAO,KAAK,CAAC;AACjB,CAAC,CAAC;AAEF,MAAM,OAAO,GAAG,CAAC,GAAW,EAAY,EAAE,CACtC,CAAC,GAAG,GAAG,CAAC,QAAQ,CAAC,kCAAkC,CAAC,CAAC;KAChD,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,WAAW,CAAC,KAAK,CAAC,CAAC,CAAC,IAAI,EAAE,EAAE,OAAO,CAAC,CAAC;KACpD,MAAM,CAAC,CAAC,KAAK,EAAmB,EAAE,CAAC,KAAK,KAAK,SAAS,CAAC,CAAC;AAGjE,MAAM,WAAW,GAAG,CAAC,GAAa,EAAuB,EAAE;IACvD,MAAM,SAAS,GAAG,MAAM,CAAC,GAAG,EAAE,wBAAwB,CAAC,CAAC;IACxD,MAAM,OAAO,GAAG,SAAS,KAAK,SAAS,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,2BAA2B,CAAC,IAAI,CAAC,SAAS,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC;IACvG,MAAM,GAAG,GAAG,OAAO,KAAK,SAAS,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,MAAM,CAAC,GAAG,EAAE,OAAO,CAAC,CAAC;IACrE,IAAI,OAAO,KAAK,SAAS,IAAI,GAAG,KAAK,SAAS,EAAE,CAAC;QAC7C,OAAO,SAAS,CAAC;IACrB,CAAC;IACD,MAAM,UAAU,GAAG,uCAAuC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;IACrE,MAAM,GAAG,GAAG,UAAU,EAAE,CAAC,CAAC,CAAC,EAAE,IAAI,EAAE,IAAI,EAAE,CAAC;IAC1C,OAAO,EAAE,GAAG,EAAE,KAAK,CAAC,OAAO,CAAC,OAAO,CAAC,EAAE,KAAK,EAAE,GAAG,KAAK,EAAE,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,cAAc,CAAC,GAAG,CAAC,EAAE,QAAQ,EAAE,UAAU,CAAC,GAAG,CAAC,EAAE,KAAK,EAAE,OAAO,CAAC,GAAG,CAAC,EAAE,CAAC;AAChJ,CAAC,CAAC;AAIF,MAAM,SAAS,GAAG,CAAC,GAAa,EAAE,GAAY,EAAE,KAAa,EAAkC,EAAE;IAC7F,MAAM,IAAI,GAAG,GAAG,CAAC,QAAQ,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;IACrC,IAAI,IAAI,KAAK,SAAS,IAAI,IAAI,CAAC,GAAG,IAAI,CAAC,QAAQ,CAAC,IAAI,CAAC,IAAI,CAAC,SAAS,CAAC,EAAE,CAAC;QACnE,OAAO,SAAS,CAAC;IACrB,CAAC;IACD,MAAM,IAAI,GAAG,KAAK,CAAC,SAAS,CAAC,KAAK,CAAC,IAAI,CAAC,GAAG,CAAC,GAAG,EAAE,kBAAkB,CAAC,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,IAAI,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;IAC5G,MAAM,IAAI,GAAG,MAAM,CAAC,GAAG,EAAE,IAAI,CAAC,CAAC;IAC/B,IAAI,IAAI,KAAK,SAAS,EAAE,CAAC;QACrB,OAAO,SAAS,CAAC;IACrB,CAAC;IACD,MAAM,GAAG,GAAG,SAAS,CAAC,IAAI,CAAC,CAAC;IAC5B,MAAM,IAAI,GAAG,MAAM,CAAC,GAAG,CAAC,CAAC;IACzB,MAAM,QAAQ,GAAG,IAAI,KAAK,SAAS,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,cAAc,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,CAAC;IACvE,IAAI,QAAQ,KAAK,EAAE,EAAE,CAAC;QAClB,OAAO,SAAS,CAAC;IACrB,CAAC;IACD,OAAO,QAAQ,CAAC,UAAU,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,MAAM,MAAM,CAAC,GAAG,CAAC,CAAC,KAAK,IAAI,KAAK,CAAC,QAAQ,CAAC,IAAI,CAAC,OAAO,QAAQ,EAAE,CAAC;AAClH,CAAC,CAAC;AAEF,MAAM,OAAO,GAAG,CAAC,QAAgB,EAAE,QAAgB,EAAE,OAAe,EAAE,MAAe,EAAY,EAAE;IAC/F,MAAM,KAAK,GAAa,EAAE,CAAC;IAC3B,IAAI,MAAM,EAAE,CAAC;QACT,KAAK,CAAC,IAAI,CAAC,WAAW,QAAQ,OAAO,QAAQ,qBAAqB,IAAI,CAAC,KAAK,CAAC,kBAAkB,GAAG,IAAI,GAAG,IAAI,CAAC,aAAa,CAAC,CAAC;IACjI,CAAC;IACD,IAAI,OAAO,GAAG,CAAC,EAAE,CAAC;QACd,KAAK,CAAC,IAAI,CAAC,GAAG,OAAO,cAAc,OAAO,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,GAAG,mDAAmD,CAAC,CAAC;IACpH,CAAC;IACD,IAAI,QAAQ,KAAK,CAAC,EAAE,CAAC;QACjB,KAAK,CAAC,IAAI,CAAC,mCAAmC,CAAC,CAAC;IACpD,CAAC;IACD,OAAO,KAAK,CAAC;AACjB,CAAC,CAAC;AAEF,MAAM,CAAC,MAAM,WAAW,GAAY;IAChC,IAAI,EAAE,MAAM;IACZ,OAAO,EAAE,CAAC;IACV,MAAM,EAAE,KAAK,EAAE,OAAO,EAAuB,EAAE;QAC3C,MAAM,GAAG,GAAG,SAAS,CAAC,IAAI,UAAU,CAAC,MAAM,QAAQ,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC;QAC/D,MAAM,GAAG,GAAG,WAAW,CAAC,GAAG,CAAC,CAAC;QAC7B,IAAI,GAAG,KAAK,SAAS,EAAE,CAAC;YACpB,OAAO,EAAE,QAAQ,EAAE,EAAE,EAAE,KAAK,EAAE,CAAC,sFAAsF,CAAC,EAAE,CAAC;QAC7H,CAAC;QACD,MAAM,QAAQ,GAAa,EAAE,CAAC;QAC9B,IAAI,KAAK,GAAG,CAAC,CAAC;QACd,IAAI,QAAQ,GAAG,CAAC,CAAC;QACjB,IAAI,OAAO,GAAG,CAAC,CAAC;QAChB,KAAK,MAAM,KAAK,IAAI,GAAG,CAAC,KAAK,EAAE,CAAC;YAC5B,MAAM,OAAO,GAAG,SAAS,CAAC,GAAG,EAAE,GAAG,EAAE,KAAK,CAAC,CAAC;YAC3C,IAAI,OAAO,KAAK,SAAS,EAAE,CAAC;gBACxB,SAAS;YACb,CAAC;YACD,IAAI,OAAO,KAAK,SAAS,EAAE,CAAC;gBACxB,OAAO,IAAI,CAAC,CAAC;gBACb,SAAS;YACb,CAAC;YACD,QAAQ,IAAI,CAAC,CAAC;YACd,IAAI,KAAK,GAAG,kBAAkB,EAAE,CAAC;gBAC7B,QAAQ,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;gBACvB,KAAK,IAAI,OAAO,CAAC,MAAM,CAAC;YAC5B,CAAC;QACL,CAAC;QACD,OAAO,EAAE,QAAQ,EAAE,QAAQ,CAAC,IAAI,CAAC,MAAM,CAAC,EAAE,KAAK,EAAE,GAAG,CAAC,KAAK,EAAE,KAAK,EAAE,OAAO,CAAC,QAAQ,CAAC,MAAM,EAAE,QAAQ,EAAE,OAAO,EAAE,KAAK,IAAI,kBAAkB,CAAC,EAAE,CAAC;IAClJ,CAAC;CACJ,CAAC"}
@@ -0,0 +1,3 @@
1
+ import type { Deriver } from "./deriver.js";
2
+ export declare const htmlDeriver: Deriver;
3
+ //# sourceMappingURL=html.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"html.d.ts","sourceRoot":"","sources":["../../../src/lib/derivers/html.ts"],"names":[],"mappings":"AAGA,OAAO,KAAK,EAAc,OAAO,EAAE,MAAM,cAAc,CAAC;AAIxD,eAAO,MAAM,WAAW,EAAE,OAazB,CAAC"}
@@ -0,0 +1,18 @@
1
+ import { readFile } from "node:fs/promises";
2
+ import { bodyOf, metaOf, parseHtml } from "@intentic/webq/dom";
3
+ import { renderMarkdown } from "@intentic/webq/markdown";
4
+ export const htmlDeriver = {
5
+ name: "html",
6
+ version: 1,
7
+ derive: async (absPath) => {
8
+ const doc = parseHtml(await readFile(absPath, "utf8"));
9
+ const body = bodyOf(doc);
10
+ const meta = metaOf(doc);
11
+ return {
12
+ markdown: body === undefined ? "" : renderMarkdown(body),
13
+ title: meta.title === "" ? undefined : meta.title,
14
+ notes: [],
15
+ };
16
+ },
17
+ };
18
+ //# sourceMappingURL=html.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"html.js","sourceRoot":"","sources":["../../../src/lib/derivers/html.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,EAAE,MAAM,kBAAkB,CAAC;AAC5C,OAAO,EAAE,MAAM,EAAE,MAAM,EAAE,SAAS,EAAE,MAAM,oBAAoB,CAAC;AAC/D,OAAO,EAAE,cAAc,EAAE,MAAM,yBAAyB,CAAC;AAKzD,MAAM,CAAC,MAAM,WAAW,GAAY;IAChC,IAAI,EAAE,MAAM;IACZ,OAAO,EAAE,CAAC;IACV,MAAM,EAAE,KAAK,EAAE,OAAO,EAAuB,EAAE;QAC3C,MAAM,GAAG,GAAG,SAAS,CAAC,MAAM,QAAQ,CAAC,OAAO,EAAE,MAAM,CAAC,CAAC,CAAC;QACvD,MAAM,IAAI,GAAG,MAAM,CAAC,GAAG,CAAC,CAAC;QACzB,MAAM,IAAI,GAAG,MAAM,CAAC,GAAG,CAAC,CAAC;QACzB,OAAO;YACH,QAAQ,EAAE,IAAI,KAAK,SAAS,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,cAAc,CAAC,IAAI,CAAC;YACxD,KAAK,EAAE,IAAI,CAAC,KAAK,KAAK,EAAE,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,IAAI,CAAC,KAAK;YACjD,KAAK,EAAE,EAAE;SACZ,CAAC;IACN,CAAC;CACJ,CAAC"}
@@ -0,0 +1,3 @@
1
+ import type { Deriver } from "./deriver.js";
2
+ export declare const imageDeriver: Deriver;
3
+ //# sourceMappingURL=image.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"image.d.ts","sourceRoot":"","sources":["../../../src/lib/derivers/image.ts"],"names":[],"mappings":"AAGA,OAAO,KAAK,EAAc,OAAO,EAAE,MAAM,cAAc,CAAC;AAqBxD,eAAO,MAAM,YAAY,EAAE,OA6B1B,CAAC"}
@@ -0,0 +1,42 @@
1
+ import { readFile } from "node:fs/promises";
2
+ import exifr from "exifr";
3
+ import { imageSize } from "image-size";
4
+ const { parse: parseExif } = exifr;
5
+ const EXIF_LINES = [
6
+ { label: "Camera", keys: ["Make", "Model"] },
7
+ { label: "Taken", keys: ["DateTimeOriginal", "CreateDate"] },
8
+ { label: "Software", keys: ["Software"] },
9
+ { label: "Orientation", keys: ["Orientation"] },
10
+ ];
11
+ export const imageDeriver = {
12
+ name: "image",
13
+ version: 1,
14
+ derive: async (absPath) => {
15
+ const bytes = await readFile(absPath);
16
+ const lines = [];
17
+ try {
18
+ const dims = imageSize(bytes);
19
+ lines.push(`- Format: ${dims.type ?? "unknown"}`, `- Dimensions: ${dims.width}×${dims.height}`);
20
+ }
21
+ catch {
22
+ lines.push("- Dimensions: unreadable");
23
+ }
24
+ const exif = (await parseExif(bytes).catch(() => undefined));
25
+ if (exif !== undefined) {
26
+ for (const { label, keys } of EXIF_LINES) {
27
+ const parts = keys.map((key) => exif[key]).filter((value) => value !== undefined && value !== "");
28
+ if (parts.length > 0) {
29
+ lines.push(`- ${label}: ${parts.map((part) => (part instanceof Date ? part.toISOString() : String(part))).join(" ")}`);
30
+ }
31
+ }
32
+ if (typeof exif["latitude"] === "number" && typeof exif["longitude"] === "number") {
33
+ lines.push(`- GPS: ${exif["latitude"].toFixed(5)}, ${exif["longitude"].toFixed(5)}`);
34
+ }
35
+ }
36
+ return {
37
+ markdown: lines.join("\n"),
38
+ notes: ["no visual description: image captioning is a later, model-backed tier — vision models should Read the image itself"],
39
+ };
40
+ },
41
+ };
42
+ //# sourceMappingURL=image.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"image.js","sourceRoot":"","sources":["../../../src/lib/derivers/image.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,EAAE,MAAM,kBAAkB,CAAC;AAC5C,OAAO,KAAK,MAAM,OAAO,CAAC;AAC1B,OAAO,EAAE,SAAS,EAAE,MAAM,YAAY,CAAC;AAOvC,MAAM,EAAE,KAAK,EAAE,SAAS,EAAE,GAAG,KAAK,CAAC;AAQnC,MAAM,UAAU,GAA4E;IACxF,EAAE,KAAK,EAAE,QAAQ,EAAE,IAAI,EAAE,CAAC,MAAM,EAAE,OAAO,CAAC,EAAE;IAC5C,EAAE,KAAK,EAAE,OAAO,EAAE,IAAI,EAAE,CAAC,kBAAkB,EAAE,YAAY,CAAC,EAAE;IAC5D,EAAE,KAAK,EAAE,UAAU,EAAE,IAAI,EAAE,CAAC,UAAU,CAAC,EAAE;IACzC,EAAE,KAAK,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,aAAa,CAAC,EAAE;CAClD,CAAC;AAEF,MAAM,CAAC,MAAM,YAAY,GAAY;IACjC,IAAI,EAAE,OAAO;IACb,OAAO,EAAE,CAAC;IACV,MAAM,EAAE,KAAK,EAAE,OAAO,EAAuB,EAAE;QAC3C,MAAM,KAAK,GAAG,MAAM,QAAQ,CAAC,OAAO,CAAC,CAAC;QACtC,MAAM,KAAK,GAAa,EAAE,CAAC;QAC3B,IAAI,CAAC;YACD,MAAM,IAAI,GAAG,SAAS,CAAC,KAAK,CAAC,CAAC;YAC9B,KAAK,CAAC,IAAI,CAAC,aAAa,IAAI,CAAC,IAAI,IAAI,SAAS,EAAE,EAAE,iBAAiB,IAAI,CAAC,KAAK,IAAI,IAAI,CAAC,MAAM,EAAE,CAAC,CAAC;QACpG,CAAC;QAAC,MAAM,CAAC;YACL,KAAK,CAAC,IAAI,CAAC,0BAA0B,CAAC,CAAC;QAC3C,CAAC;QACD,MAAM,IAAI,GAAG,CAAC,MAAM,SAAS,CAAC,KAAK,CAAC,CAAC,KAAK,CAAC,GAAG,EAAE,CAAC,SAAS,CAAC,CAAwC,CAAC;QACpG,IAAI,IAAI,KAAK,SAAS,EAAE,CAAC;YACrB,KAAK,MAAM,EAAE,KAAK,EAAE,IAAI,EAAE,IAAI,UAAU,EAAE,CAAC;gBACvC,MAAM,KAAK,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,KAAK,SAAS,IAAI,KAAK,KAAK,EAAE,CAAC,CAAC;gBAClG,IAAI,KAAK,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;oBACnB,KAAK,CAAC,IAAI,CAAC,KAAK,KAAK,KAAK,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC,IAAI,YAAY,IAAI,CAAC,CAAC,CAAC,IAAI,CAAC,WAAW,EAAE,CAAC,CAAC,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC;gBAC3H,CAAC;YACL,CAAC;YACD,IAAI,OAAO,IAAI,CAAC,UAAU,CAAC,KAAK,QAAQ,IAAI,OAAO,IAAI,CAAC,WAAW,CAAC,KAAK,QAAQ,EAAE,CAAC;gBAChF,KAAK,CAAC,IAAI,CAAC,UAAU,IAAI,CAAC,UAAU,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,KAAK,IAAI,CAAC,WAAW,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC;YACzF,CAAC;QACL,CAAC;QACD,OAAO;YACH,QAAQ,EAAE,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC;YAC1B,KAAK,EAAE,CAAC,oHAAoH,CAAC;SAChI,CAAC;IACN,CAAC;CACJ,CAAC"}
@@ -0,0 +1,3 @@
1
+ import type { Deriver } from "./deriver.js";
2
+ export declare const ipynbDeriver: Deriver;
3
+ //# sourceMappingURL=ipynb.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"ipynb.d.ts","sourceRoot":"","sources":["../../../src/lib/derivers/ipynb.ts"],"names":[],"mappings":"AAEA,OAAO,KAAK,EAAc,OAAO,EAAE,MAAM,cAAc,CAAC;AA8FxD,eAAO,MAAM,YAAY,EAAE,OAgB1B,CAAC"}