@tenphi/akno-core 0.3.0 → 0.5.0
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.
- package/README.md +4 -2
- package/config/default.jsonc +16 -10
- package/dist/config/load.d.ts +5 -2
- package/dist/config/load.d.ts.map +1 -1
- package/dist/config/load.js +26 -12
- package/dist/config/load.js.map +1 -1
- package/dist/config/schema.d.ts +2 -2
- package/dist/config/schema.js +2 -2
- package/dist/config/schema.js.map +1 -1
- package/dist/config/write-setup.d.ts +2 -0
- package/dist/config/write-setup.d.ts.map +1 -1
- package/dist/config/write-setup.js +7 -3
- package/dist/config/write-setup.js.map +1 -1
- package/dist/doctor.d.ts +2 -5
- package/dist/doctor.d.ts.map +1 -1
- package/dist/doctor.js.map +1 -1
- package/dist/index/derive.d.ts.map +1 -1
- package/dist/index/derive.js +2 -11
- package/dist/index/derive.js.map +1 -1
- package/dist/ingest/extract.d.ts +14 -4
- package/dist/ingest/extract.d.ts.map +1 -1
- package/dist/ingest/extract.js +142 -26
- package/dist/ingest/extract.js.map +1 -1
- package/dist/ingest/extractor-contract.d.ts +63 -0
- package/dist/ingest/extractor-contract.d.ts.map +1 -0
- package/dist/ingest/extractor-contract.js +26 -0
- package/dist/ingest/extractor-contract.js.map +1 -0
- package/dist/ingest/linux-extractor.d.ts +32 -0
- package/dist/ingest/linux-extractor.d.ts.map +1 -0
- package/dist/ingest/linux-extractor.js +344 -0
- package/dist/ingest/linux-extractor.js.map +1 -0
- package/dist/kb/managed-lines.d.ts +4 -0
- package/dist/kb/managed-lines.d.ts.map +1 -0
- package/dist/kb/managed-lines.js +37 -0
- package/dist/kb/managed-lines.js.map +1 -0
- package/dist/maintenance/conflicts.d.ts +1 -1
- package/dist/open.d.ts +1 -1
- package/dist/open.d.ts.map +1 -1
- package/dist/ops/answer.d.ts.map +1 -1
- package/dist/ops/answer.js +14 -2
- package/dist/ops/answer.js.map +1 -1
- package/dist/ops/read.d.ts.map +1 -1
- package/dist/ops/read.js +2 -1
- package/dist/ops/read.js.map +1 -1
- package/dist/ops/remember.d.ts +57 -0
- package/dist/ops/remember.d.ts.map +1 -1
- package/dist/ops/remember.js +40 -38
- package/dist/ops/remember.js.map +1 -1
- package/dist/ops/retain.d.ts.map +1 -1
- package/dist/ops/retain.js +262 -31
- package/dist/ops/retain.js.map +1 -1
- package/dist/recall/assemble.d.ts.map +1 -1
- package/dist/recall/assemble.js +4 -2
- package/dist/recall/assemble.js.map +1 -1
- package/dist/store/db.d.ts.map +1 -1
- package/dist/store/db.js +8 -1
- package/dist/store/db.js.map +1 -1
- package/dist/store/migrations.d.ts +2 -1
- package/dist/store/migrations.d.ts.map +1 -1
- package/dist/store/migrations.js +56 -1
- package/dist/store/migrations.js.map +1 -1
- package/dist/watch/watcher.d.ts +3 -3
- package/dist/watch/watcher.js +5 -5
- package/dist/watch/watcher.js.map +1 -1
- package/dist/write/managed-memory.d.ts +6 -0
- package/dist/write/managed-memory.d.ts.map +1 -1
- package/dist/write/managed-memory.js +16 -0
- package/dist/write/managed-memory.js.map +1 -1
- package/dist/write/placement.d.ts +3 -1
- package/dist/write/placement.d.ts.map +1 -1
- package/dist/write/placement.js +4 -1
- package/dist/write/placement.js.map +1 -1
- package/dist/write/retain.d.ts +158 -30
- package/dist/write/retain.d.ts.map +1 -1
- package/dist/write/retain.js +722 -180
- package/dist/write/retain.js.map +1 -1
- package/package.json +4 -3
|
@@ -0,0 +1,32 @@
|
|
|
1
|
+
import type { DocumentExtractorBackend } from './extractor-contract.ts';
|
|
2
|
+
type LinuxExecuteFile = (command: string, args: string[], options: {
|
|
3
|
+
maxBuffer: number;
|
|
4
|
+
timeout: number;
|
|
5
|
+
killSignal: NodeJS.Signals;
|
|
6
|
+
}) => Promise<{
|
|
7
|
+
stdout: string;
|
|
8
|
+
stderr: string;
|
|
9
|
+
}>;
|
|
10
|
+
export interface LinuxCommandRunner {
|
|
11
|
+
available(command: string): Promise<boolean>;
|
|
12
|
+
makeTempDir(): Promise<string>;
|
|
13
|
+
readText(file: string): Promise<string>;
|
|
14
|
+
removeTempDir(directory: string): Promise<void>;
|
|
15
|
+
run(command: string, args: string[]): Promise<{
|
|
16
|
+
stdout: string;
|
|
17
|
+
}>;
|
|
18
|
+
}
|
|
19
|
+
export declare function createNodeLinuxCommandRunner(execute?: LinuxExecuteFile): LinuxCommandRunner;
|
|
20
|
+
export interface LinuxExtractionCapabilities {
|
|
21
|
+
backend: 'linux-native';
|
|
22
|
+
libreoffice: boolean;
|
|
23
|
+
pdfinfo: boolean;
|
|
24
|
+
pdftotext: boolean;
|
|
25
|
+
pdftoppm: boolean;
|
|
26
|
+
tesseract: boolean;
|
|
27
|
+
note: string | null;
|
|
28
|
+
}
|
|
29
|
+
export declare function linuxExtractionCapabilities(commands: LinuxCommandRunner): Promise<LinuxExtractionCapabilities>;
|
|
30
|
+
export declare function createLinuxDocumentExtractor(commands: LinuxCommandRunner): DocumentExtractorBackend;
|
|
31
|
+
export {};
|
|
32
|
+
//# sourceMappingURL=linux-extractor.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"linux-extractor.d.ts","sourceRoot":"","sources":["../../src/ingest/linux-extractor.ts"],"names":[],"mappings":"AAOA,OAAO,KAAK,EAEV,wBAAwB,EAEzB,MAAM,yBAAyB,CAAC;AAOjC,KAAK,gBAAgB,GAAG,CACtB,OAAO,EAAE,MAAM,EACf,IAAI,EAAE,MAAM,EAAE,EACd,OAAO,EAAE;IAAE,SAAS,EAAE,MAAM,CAAC;IAAC,OAAO,EAAE,MAAM,CAAC;IAAC,UAAU,EAAE,MAAM,CAAC,OAAO,CAAA;CAAE,KACxE,OAAO,CAAC;IAAE,MAAM,EAAE,MAAM,CAAC;IAAC,MAAM,EAAE,MAAM,CAAA;CAAE,CAAC,CAAC;AAOjD,MAAM,WAAW,kBAAkB;IACjC,SAAS,CAAC,OAAO,EAAE,MAAM,GAAG,OAAO,CAAC,OAAO,CAAC,CAAC;IAC7C,WAAW,IAAI,OAAO,CAAC,MAAM,CAAC,CAAC;IAC/B,QAAQ,CAAC,IAAI,EAAE,MAAM,GAAG,OAAO,CAAC,MAAM,CAAC,CAAC;IACxC,aAAa,CAAC,SAAS,EAAE,MAAM,GAAG,OAAO,CAAC,IAAI,CAAC,CAAC;IAChD,GAAG,CAAC,OAAO,EAAE,MAAM,EAAE,IAAI,EAAE,MAAM,EAAE,GAAG,OAAO,CAAC;QAAE,MAAM,EAAE,MAAM,CAAA;KAAE,CAAC,CAAC;CACnE;AAED,wBAAgB,4BAA4B,CAAC,OAAO,GAAE,gBAA8B,GAAG,kBAAkB,CAexG;AAkBD,MAAM,WAAW,2BAA2B;IAC1C,OAAO,EAAE,cAAc,CAAC;IACxB,WAAW,EAAE,OAAO,CAAC;IACrB,OAAO,EAAE,OAAO,CAAC;IACjB,SAAS,EAAE,OAAO,CAAC;IACnB,QAAQ,EAAE,OAAO,CAAC;IAClB,SAAS,EAAE,OAAO,CAAC;IACnB,IAAI,EAAE,MAAM,GAAG,IAAI,CAAC;CACrB;AAED,wBAAsB,2BAA2B,CAC/C,QAAQ,EAAE,kBAAkB,GAC3B,OAAO,CAAC,2BAA2B,CAAC,CAgBtC;AAED,wBAAgB,4BAA4B,CAAC,QAAQ,EAAE,kBAAkB,GAAG,wBAAwB,CAcnG"}
|
|
@@ -0,0 +1,344 @@
|
|
|
1
|
+
import { execFile } from 'node:child_process';
|
|
2
|
+
import fs from 'node:fs';
|
|
3
|
+
import fsp from 'node:fs/promises';
|
|
4
|
+
import os from 'node:os';
|
|
5
|
+
import path from 'node:path';
|
|
6
|
+
import { pathToFileURL } from 'node:url';
|
|
7
|
+
import { promisify } from 'node:util';
|
|
8
|
+
const IMAGE_EXTENSIONS = new Set(['.png', '.jpg', '.jpeg', '.webp', '.tiff', '.tif', '.gif', '.bmp']);
|
|
9
|
+
const OFFICE_EXTENSIONS = new Set(['.doc', '.docx', '.odt', '.rtf']);
|
|
10
|
+
const MIN_USABLE_PDF_PAGE_CHARACTERS = 40;
|
|
11
|
+
const runFile = promisify(execFile);
|
|
12
|
+
const executeFile = async (command, args, options) => {
|
|
13
|
+
const result = await runFile(command, args, options);
|
|
14
|
+
return { stdout: String(result.stdout), stderr: String(result.stderr) };
|
|
15
|
+
};
|
|
16
|
+
export function createNodeLinuxCommandRunner(execute = executeFile) {
|
|
17
|
+
return {
|
|
18
|
+
available: commandAvailable,
|
|
19
|
+
makeTempDir: async () => fsp.mkdtemp(path.join(os.tmpdir(), 'akno-extract-')),
|
|
20
|
+
readText: async (file) => fsp.readFile(file, 'utf8'),
|
|
21
|
+
removeTempDir: async (directory) => fsp.rm(directory, { force: true, recursive: true }),
|
|
22
|
+
run: async (command, args) => {
|
|
23
|
+
const { stdout } = await execute(command, args, {
|
|
24
|
+
maxBuffer: 10 * 1_048_576,
|
|
25
|
+
timeout: 300_000,
|
|
26
|
+
killSignal: 'SIGKILL',
|
|
27
|
+
});
|
|
28
|
+
return { stdout };
|
|
29
|
+
},
|
|
30
|
+
};
|
|
31
|
+
}
|
|
32
|
+
async function commandAvailable(command) {
|
|
33
|
+
if (path.isAbsolute(command))
|
|
34
|
+
return executable(command);
|
|
35
|
+
const directories = (process.env.PATH ?? '').split(path.delimiter).filter(Boolean);
|
|
36
|
+
const matches = await Promise.all(directories.map((directory) => executable(path.join(directory, command))));
|
|
37
|
+
return matches.some(Boolean);
|
|
38
|
+
}
|
|
39
|
+
async function executable(candidate) {
|
|
40
|
+
return fsp
|
|
41
|
+
.access(candidate, fs.constants.X_OK)
|
|
42
|
+
.then(() => true)
|
|
43
|
+
.catch(() => false);
|
|
44
|
+
}
|
|
45
|
+
export async function linuxExtractionCapabilities(commands) {
|
|
46
|
+
const names = ['libreoffice', 'pdfinfo', 'pdftotext', 'pdftoppm', 'tesseract'];
|
|
47
|
+
const available = await Promise.all(names.map((name) => commands.available(name)));
|
|
48
|
+
const tools = Object.fromEntries(names.map((name, index) => [name, available[index]]));
|
|
49
|
+
const popplerNames = ['pdfinfo', 'pdftotext', 'pdftoppm'];
|
|
50
|
+
const missingPoppler = popplerNames.filter((name) => !tools[name]);
|
|
51
|
+
let note = null;
|
|
52
|
+
if (missingPoppler.length > 0) {
|
|
53
|
+
note = `PDF extraction is unavailable: install Poppler (${missingPoppler.join(', ')} missing).`;
|
|
54
|
+
}
|
|
55
|
+
else if (!tools.tesseract) {
|
|
56
|
+
note = 'OCR is unavailable: install tesseract. PDF text-layer extraction remains available.';
|
|
57
|
+
}
|
|
58
|
+
return { backend: 'linux-native', ...tools, note };
|
|
59
|
+
}
|
|
60
|
+
export function createLinuxDocumentExtractor(commands) {
|
|
61
|
+
return {
|
|
62
|
+
name: 'linux-native',
|
|
63
|
+
extract: async (request) => {
|
|
64
|
+
const extension = path.extname(request.absPath).toLowerCase();
|
|
65
|
+
if (extension === '.pdf')
|
|
66
|
+
return extractPdf(request.absPath, request.maxOcrPages, commands);
|
|
67
|
+
if (IMAGE_EXTENSIONS.has(extension))
|
|
68
|
+
return ocrImage(request.absPath, commands);
|
|
69
|
+
if (OFFICE_EXTENSIONS.has(extension))
|
|
70
|
+
return extractOffice(request.absPath, commands);
|
|
71
|
+
return failed(`no Linux extractor for ${extension || 'a file with no extension'}`, {
|
|
72
|
+
backend: 'linux-native',
|
|
73
|
+
tool: null,
|
|
74
|
+
});
|
|
75
|
+
},
|
|
76
|
+
};
|
|
77
|
+
}
|
|
78
|
+
async function extractOffice(absPath, commands) {
|
|
79
|
+
const missing = await missingCommands(['libreoffice'], commands);
|
|
80
|
+
if (missing.length > 0)
|
|
81
|
+
return missingDependency('Office extraction requires libreoffice', missing);
|
|
82
|
+
const directory = await commands.makeTempDir();
|
|
83
|
+
try {
|
|
84
|
+
await commands.run('libreoffice', [
|
|
85
|
+
`-env:UserInstallation=${pathToFileURL(path.join(directory, 'profile')).href}`,
|
|
86
|
+
'--headless',
|
|
87
|
+
'--convert-to',
|
|
88
|
+
'txt:Text',
|
|
89
|
+
'--outdir',
|
|
90
|
+
directory,
|
|
91
|
+
absPath,
|
|
92
|
+
]);
|
|
93
|
+
const output = path.join(directory, `${path.parse(absPath).name}.txt`);
|
|
94
|
+
const text = (await commands.readText(output)).trim();
|
|
95
|
+
return text
|
|
96
|
+
? {
|
|
97
|
+
text,
|
|
98
|
+
pages: null,
|
|
99
|
+
ocr: false,
|
|
100
|
+
confidence: null,
|
|
101
|
+
provenance: { backend: 'linux-native', tool: 'libreoffice' },
|
|
102
|
+
text_from: 'libreoffice',
|
|
103
|
+
degradation: null,
|
|
104
|
+
}
|
|
105
|
+
: failed('libreoffice found no text', { backend: 'linux-native', tool: 'libreoffice' });
|
|
106
|
+
}
|
|
107
|
+
catch (error) {
|
|
108
|
+
return failed(`libreoffice could not read the file: ${errorMessage(error)}`, {
|
|
109
|
+
backend: 'linux-native',
|
|
110
|
+
tool: 'libreoffice',
|
|
111
|
+
});
|
|
112
|
+
}
|
|
113
|
+
finally {
|
|
114
|
+
await commands.removeTempDir(directory);
|
|
115
|
+
}
|
|
116
|
+
}
|
|
117
|
+
async function extractPdf(absPath, maxOcrPages, commands) {
|
|
118
|
+
const missing = await missingCommands(['pdfinfo', 'pdftotext'], commands);
|
|
119
|
+
if (missing.length > 0)
|
|
120
|
+
return missingDependency('PDF extraction requires Poppler tools', missing);
|
|
121
|
+
let info;
|
|
122
|
+
try {
|
|
123
|
+
({ stdout: info } = await commands.run('pdfinfo', [absPath]));
|
|
124
|
+
}
|
|
125
|
+
catch (error) {
|
|
126
|
+
return failed(`pdfinfo could not inspect the PDF: ${errorMessage(error)}`, {
|
|
127
|
+
backend: 'linux-native',
|
|
128
|
+
tool: 'pdfinfo',
|
|
129
|
+
});
|
|
130
|
+
}
|
|
131
|
+
const count = Number(/^Pages:\s+(\d+)\s*$/m.exec(info)?.[1] ?? 0);
|
|
132
|
+
if (count < 1) {
|
|
133
|
+
return failed('pdfinfo did not report a positive page count', {
|
|
134
|
+
backend: 'linux-native',
|
|
135
|
+
tool: 'pdfinfo',
|
|
136
|
+
});
|
|
137
|
+
}
|
|
138
|
+
let stdout;
|
|
139
|
+
try {
|
|
140
|
+
({ stdout } = await commands.run('pdftotext', ['-layout', absPath, '-']));
|
|
141
|
+
}
|
|
142
|
+
catch (error) {
|
|
143
|
+
return failed(`pdftotext could not read the PDF: ${errorMessage(error)}`, {
|
|
144
|
+
backend: 'linux-native',
|
|
145
|
+
tool: 'pdftotext',
|
|
146
|
+
});
|
|
147
|
+
}
|
|
148
|
+
const pageText = stdout.split('\f');
|
|
149
|
+
// Match the macOS extractor's 40-character scan guard per page. A page number or
|
|
150
|
+
// typed cover sheet must not hide scanned pages elsewhere in the same document.
|
|
151
|
+
const allSections = Array.from({ length: count }, (_, index) => ({
|
|
152
|
+
page: index + 1,
|
|
153
|
+
text: (pageText[index] ?? '').trim(),
|
|
154
|
+
}));
|
|
155
|
+
const sections = allSections.filter((section) => section.text.length >= MIN_USABLE_PDF_PAGE_CHARACTERS);
|
|
156
|
+
const pagesNeedingOcr = allSections
|
|
157
|
+
.filter((section) => section.text.length < MIN_USABLE_PDF_PAGE_CHARACTERS)
|
|
158
|
+
.map((section) => section.page);
|
|
159
|
+
if (pagesNeedingOcr.length > 0) {
|
|
160
|
+
return ocrPdf(absPath, count, pagesNeedingOcr, sections, maxOcrPages, commands);
|
|
161
|
+
}
|
|
162
|
+
const text = sections.map((section) => section.text).join('\n\n');
|
|
163
|
+
return {
|
|
164
|
+
text,
|
|
165
|
+
pages: { count, sections },
|
|
166
|
+
ocr: false,
|
|
167
|
+
confidence: null,
|
|
168
|
+
provenance: { backend: 'linux-native', tool: 'pdftotext' },
|
|
169
|
+
text_from: 'text-layer',
|
|
170
|
+
degradation: null,
|
|
171
|
+
};
|
|
172
|
+
}
|
|
173
|
+
async function ocrImage(absPath, commands) {
|
|
174
|
+
const missing = await missingCommands(['tesseract'], commands);
|
|
175
|
+
if (missing.length > 0)
|
|
176
|
+
return missingDependency('Image OCR requires tesseract', missing);
|
|
177
|
+
try {
|
|
178
|
+
const { stdout } = await commands.run('tesseract', [absPath, 'stdout', 'tsv']);
|
|
179
|
+
const recognized = parseTesseractTsv(stdout);
|
|
180
|
+
return {
|
|
181
|
+
text: recognized.text,
|
|
182
|
+
pages: {
|
|
183
|
+
count: 1,
|
|
184
|
+
sections: recognized.text ? [{ page: 1, text: recognized.text }] : [],
|
|
185
|
+
},
|
|
186
|
+
ocr: true,
|
|
187
|
+
confidence: meanConfidence(recognized.confidences),
|
|
188
|
+
provenance: { backend: 'linux-native', tool: 'tesseract' },
|
|
189
|
+
text_from: 'ocr',
|
|
190
|
+
degradation: null,
|
|
191
|
+
};
|
|
192
|
+
}
|
|
193
|
+
catch (error) {
|
|
194
|
+
return failed(`tesseract could not OCR the image: ${errorMessage(error)}`, {
|
|
195
|
+
backend: 'linux-native',
|
|
196
|
+
tool: 'tesseract',
|
|
197
|
+
});
|
|
198
|
+
}
|
|
199
|
+
}
|
|
200
|
+
async function ocrPdf(absPath, pageCount, pagesNeedingOcr, textLayerSections, maxOcrPages, commands) {
|
|
201
|
+
const missing = await missingCommands(['pdftoppm', 'tesseract'], commands);
|
|
202
|
+
if (missing.length > 0) {
|
|
203
|
+
const result = missingDependency('Scanned PDF OCR requires pdftoppm and tesseract', missing);
|
|
204
|
+
if (textLayerSections.length === 0)
|
|
205
|
+
return result;
|
|
206
|
+
return {
|
|
207
|
+
...result,
|
|
208
|
+
text: textLayerSections.map((section) => section.text).join('\n\n'),
|
|
209
|
+
pages: { count: pageCount, sections: textLayerSections },
|
|
210
|
+
provenance: { backend: 'linux-native', tool: 'pdftotext' },
|
|
211
|
+
text_from: 'text-layer',
|
|
212
|
+
};
|
|
213
|
+
}
|
|
214
|
+
const directory = await commands.makeTempDir();
|
|
215
|
+
const pagesToRead = pagesNeedingOcr.slice(0, Math.max(0, maxOcrPages));
|
|
216
|
+
const sections = [...textLayerSections];
|
|
217
|
+
const confidences = [];
|
|
218
|
+
let ocrPagesRead = 0;
|
|
219
|
+
let tool = 'pdftoppm';
|
|
220
|
+
try {
|
|
221
|
+
for (const page of pagesToRead) {
|
|
222
|
+
const prefix = path.join(directory, `page-${page}`);
|
|
223
|
+
tool = 'pdftoppm';
|
|
224
|
+
await commands.run('pdftoppm', [
|
|
225
|
+
'-f',
|
|
226
|
+
String(page),
|
|
227
|
+
'-l',
|
|
228
|
+
String(page),
|
|
229
|
+
'-singlefile',
|
|
230
|
+
'-png',
|
|
231
|
+
'-r',
|
|
232
|
+
'300',
|
|
233
|
+
absPath,
|
|
234
|
+
prefix,
|
|
235
|
+
]);
|
|
236
|
+
tool = 'tesseract';
|
|
237
|
+
const { stdout } = await commands.run('tesseract', [`${prefix}.png`, 'stdout', 'tsv']);
|
|
238
|
+
const recognized = parseTesseractTsv(stdout);
|
|
239
|
+
if (recognized.text)
|
|
240
|
+
sections.push({ page, text: recognized.text });
|
|
241
|
+
confidences.push(...recognized.confidences);
|
|
242
|
+
ocrPagesRead += 1;
|
|
243
|
+
}
|
|
244
|
+
}
|
|
245
|
+
catch (error) {
|
|
246
|
+
if (sections.length > 0) {
|
|
247
|
+
const ordered = sections.sort((left, right) => left.page - right.page);
|
|
248
|
+
return {
|
|
249
|
+
text: ordered.map((section) => section.text).join('\n\n'),
|
|
250
|
+
pages: { count: pageCount, sections: ordered },
|
|
251
|
+
ocr: ocrPagesRead > 0,
|
|
252
|
+
confidence: meanConfidence(confidences),
|
|
253
|
+
provenance: { backend: 'linux-native', tool },
|
|
254
|
+
text_from: ocrPagesRead > 0 ? 'ocr' : 'text-layer',
|
|
255
|
+
degradation: {
|
|
256
|
+
kind: 'partial-extraction',
|
|
257
|
+
message: `scanned: OCR failed on page ${pagesToRead[ocrPagesRead]} after reading ${sections.length} of ${pageCount} pages: ${errorMessage(error)}`,
|
|
258
|
+
pages_read: sections.length,
|
|
259
|
+
pages_total: pageCount,
|
|
260
|
+
},
|
|
261
|
+
};
|
|
262
|
+
}
|
|
263
|
+
return failed(`scanned PDF OCR failed: ${errorMessage(error)}`, {
|
|
264
|
+
backend: 'linux-native',
|
|
265
|
+
tool,
|
|
266
|
+
});
|
|
267
|
+
}
|
|
268
|
+
finally {
|
|
269
|
+
await commands.removeTempDir(directory);
|
|
270
|
+
}
|
|
271
|
+
const ordered = sections.sort((left, right) => left.page - right.page);
|
|
272
|
+
const text = ordered.map((section) => section.text).join('\n\n');
|
|
273
|
+
return {
|
|
274
|
+
text,
|
|
275
|
+
pages: { count: pageCount, sections: ordered },
|
|
276
|
+
ocr: true,
|
|
277
|
+
confidence: meanConfidence(confidences),
|
|
278
|
+
provenance: { backend: 'linux-native', tool: 'tesseract' },
|
|
279
|
+
text_from: 'ocr',
|
|
280
|
+
degradation: pagesToRead.length < pagesNeedingOcr.length
|
|
281
|
+
? {
|
|
282
|
+
kind: 'partial-extraction',
|
|
283
|
+
message: `scanned: OCR read the first ${sections.length} of ${pageCount} pages`,
|
|
284
|
+
pages_read: sections.length,
|
|
285
|
+
pages_total: pageCount,
|
|
286
|
+
}
|
|
287
|
+
: null,
|
|
288
|
+
};
|
|
289
|
+
}
|
|
290
|
+
function parseTesseractTsv(tsv) {
|
|
291
|
+
const lines = new Map();
|
|
292
|
+
const confidences = [];
|
|
293
|
+
for (const row of tsv.split(/\r?\n/).slice(1)) {
|
|
294
|
+
const fields = row.split('\t');
|
|
295
|
+
if (fields[0] !== '5')
|
|
296
|
+
continue;
|
|
297
|
+
const text = fields.slice(11).join('\t').trim();
|
|
298
|
+
if (!text)
|
|
299
|
+
continue;
|
|
300
|
+
const line = fields.slice(1, 5).join(':');
|
|
301
|
+
const words = lines.get(line) ?? [];
|
|
302
|
+
words.push(text);
|
|
303
|
+
lines.set(line, words);
|
|
304
|
+
const confidence = Number(fields[10]);
|
|
305
|
+
if (Number.isFinite(confidence) && confidence >= 0)
|
|
306
|
+
confidences.push(confidence);
|
|
307
|
+
}
|
|
308
|
+
return { text: [...lines.values()].map((words) => words.join(' ')).join('\n'), confidences };
|
|
309
|
+
}
|
|
310
|
+
function meanConfidence(confidences) {
|
|
311
|
+
return confidences.length > 0
|
|
312
|
+
? confidences.reduce((total, confidence) => total + confidence, 0) / confidences.length / 100
|
|
313
|
+
: null;
|
|
314
|
+
}
|
|
315
|
+
async function missingCommands(commandsToCheck, commands) {
|
|
316
|
+
const available = await Promise.all(commandsToCheck.map((command) => commands.available(command)));
|
|
317
|
+
return commandsToCheck.filter((_, index) => !available[index]);
|
|
318
|
+
}
|
|
319
|
+
function missingDependency(message, tools) {
|
|
320
|
+
return {
|
|
321
|
+
text: '',
|
|
322
|
+
pages: null,
|
|
323
|
+
ocr: false,
|
|
324
|
+
confidence: null,
|
|
325
|
+
provenance: { backend: 'linux-native', tool: null },
|
|
326
|
+
text_from: 'none',
|
|
327
|
+
degradation: { kind: 'missing-dependency', message: `${message}: ${tools.join(', ')}`, tools },
|
|
328
|
+
};
|
|
329
|
+
}
|
|
330
|
+
function errorMessage(error) {
|
|
331
|
+
return error instanceof Error ? error.message : String(error);
|
|
332
|
+
}
|
|
333
|
+
function failed(message, provenance) {
|
|
334
|
+
return {
|
|
335
|
+
text: '',
|
|
336
|
+
pages: null,
|
|
337
|
+
ocr: false,
|
|
338
|
+
confidence: null,
|
|
339
|
+
provenance,
|
|
340
|
+
text_from: 'none',
|
|
341
|
+
degradation: { kind: 'extraction-failed', message },
|
|
342
|
+
};
|
|
343
|
+
}
|
|
344
|
+
//# sourceMappingURL=linux-extractor.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"linux-extractor.js","sourceRoot":"","sources":["../../src/ingest/linux-extractor.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,EAAE,MAAM,oBAAoB,CAAC;AAC9C,OAAO,EAAE,MAAM,SAAS,CAAC;AACzB,OAAO,GAAG,MAAM,kBAAkB,CAAC;AACnC,OAAO,EAAE,MAAM,SAAS,CAAC;AACzB,OAAO,IAAI,MAAM,WAAW,CAAC;AAC7B,OAAO,EAAE,aAAa,EAAE,MAAM,UAAU,CAAC;AACzC,OAAO,EAAE,SAAS,EAAE,MAAM,WAAW,CAAC;AAOtC,MAAM,gBAAgB,GAAG,IAAI,GAAG,CAAC,CAAC,MAAM,EAAE,MAAM,EAAE,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,MAAM,EAAE,MAAM,EAAE,MAAM,CAAC,CAAC,CAAC;AACtG,MAAM,iBAAiB,GAAG,IAAI,GAAG,CAAC,CAAC,MAAM,EAAE,OAAO,EAAE,MAAM,EAAE,MAAM,CAAC,CAAC,CAAC;AACrE,MAAM,8BAA8B,GAAG,EAAE,CAAC;AAC1C,MAAM,OAAO,GAAG,SAAS,CAAC,QAAQ,CAAC,CAAC;AAQpC,MAAM,WAAW,GAAqB,KAAK,EAAE,OAAO,EAAE,IAAI,EAAE,OAAO,EAAE,EAAE;IACrE,MAAM,MAAM,GAAG,MAAM,OAAO,CAAC,OAAO,EAAE,IAAI,EAAE,OAAO,CAAC,CAAC;IACrD,OAAO,EAAE,MAAM,EAAE,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,EAAE,MAAM,EAAE,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,EAAE,CAAC;AAC1E,CAAC,CAAC;AAUF,MAAM,UAAU,4BAA4B,CAAC,UAA4B,WAAW;IAClF,OAAO;QACL,SAAS,EAAE,gBAAgB;QAC3B,WAAW,EAAE,KAAK,IAAI,EAAE,CAAC,GAAG,CAAC,OAAO,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC,MAAM,EAAE,EAAE,eAAe,CAAC,CAAC;QAC7E,QAAQ,EAAE,KAAK,EAAE,IAAI,EAAE,EAAE,CAAC,GAAG,CAAC,QAAQ,CAAC,IAAI,EAAE,MAAM,CAAC;QACpD,aAAa,EAAE,KAAK,EAAE,SAAS,EAAE,EAAE,CAAC,GAAG,CAAC,EAAE,CAAC,SAAS,EAAE,EAAE,KAAK,EAAE,IAAI,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC;QACvF,GAAG,EAAE,KAAK,EAAE,OAAO,EAAE,IAAI,EAAE,EAAE;YAC3B,MAAM,EAAE,MAAM,EAAE,GAAG,MAAM,OAAO,CAAC,OAAO,EAAE,IAAI,EAAE;gBAC9C,SAAS,EAAE,EAAE,GAAG,SAAS;gBACzB,OAAO,EAAE,OAAO;gBAChB,UAAU,EAAE,SAAS;aACtB,CAAC,CAAC;YACH,OAAO,EAAE,MAAM,EAAE,CAAC;QACpB,CAAC;KACF,CAAC;AACJ,CAAC;AAED,KAAK,UAAU,gBAAgB,CAAC,OAAe;IAC7C,IAAI,IAAI,CAAC,UAAU,CAAC,OAAO,CAAC;QAAE,OAAO,UAAU,CAAC,OAAO,CAAC,CAAC;IACzD,MAAM,WAAW,GAAG,CAAC,OAAO,CAAC,GAAG,CAAC,IAAI,IAAI,EAAE,CAAC,CAAC,KAAK,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC;IACnF,MAAM,OAAO,GAAG,MAAM,OAAO,CAAC,GAAG,CAC/B,WAAW,CAAC,GAAG,CAAC,CAAC,SAAS,EAAE,EAAE,CAAC,UAAU,CAAC,IAAI,CAAC,IAAI,CAAC,SAAS,EAAE,OAAO,CAAC,CAAC,CAAC,CAC1E,CAAC;IACF,OAAO,OAAO,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;AAC/B,CAAC;AAED,KAAK,UAAU,UAAU,CAAC,SAAiB;IACzC,OAAO,GAAG;SACP,MAAM,CAAC,SAAS,EAAE,EAAE,CAAC,SAAS,CAAC,IAAI,CAAC;SACpC,IAAI,CAAC,GAAG,EAAE,CAAC,IAAI,CAAC;SAChB,KAAK,CAAC,GAAG,EAAE,CAAC,KAAK,CAAC,CAAC;AACxB,CAAC;AAYD,MAAM,CAAC,KAAK,UAAU,2BAA2B,CAC/C,QAA4B;IAE5B,MAAM,KAAK,GAAG,CAAC,aAAa,EAAE,SAAS,EAAE,WAAW,EAAE,UAAU,EAAE,WAAW,CAAU,CAAC;IACxF,MAAM,SAAS,GAAG,MAAM,OAAO,CAAC,GAAG,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,QAAQ,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;IACnF,MAAM,KAAK,GAAG,MAAM,CAAC,WAAW,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,KAAK,EAAE,EAAE,CAAC,CAAC,IAAI,EAAE,SAAS,CAAC,KAAK,CAAC,CAAC,CAAC,CAGpF,CAAC;IACF,MAAM,YAAY,GAAG,CAAC,SAAS,EAAE,WAAW,EAAE,UAAU,CAAU,CAAC;IACnE,MAAM,cAAc,GAAG,YAAY,CAAC,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,CAAC;IACnE,IAAI,IAAI,GAAkB,IAAI,CAAC;IAC/B,IAAI,cAAc,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QAC9B,IAAI,GAAG,mDAAmD,cAAc,CAAC,IAAI,CAAC,IAAI,CAAC,YAAY,CAAC;IAClG,CAAC;SAAM,IAAI,CAAC,KAAK,CAAC,SAAS,EAAE,CAAC;QAC5B,IAAI,GAAG,qFAAqF,CAAC;IAC/F,CAAC;IACD,OAAO,EAAE,OAAO,EAAE,cAAc,EAAE,GAAG,KAAK,EAAE,IAAI,EAAE,CAAC;AACrD,CAAC;AAED,MAAM,UAAU,4BAA4B,CAAC,QAA4B;IACvE,OAAO;QACL,IAAI,EAAE,cAAc;QACpB,OAAO,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE;YACzB,MAAM,SAAS,GAAG,IAAI,CAAC,OAAO,CAAC,OAAO,CAAC,OAAO,CAAC,CAAC,WAAW,EAAE,CAAC;YAC9D,IAAI,SAAS,KAAK,MAAM;gBAAE,OAAO,UAAU,CAAC,OAAO,CAAC,OAAO,EAAE,OAAO,CAAC,WAAW,EAAE,QAAQ,CAAC,CAAC;YAC5F,IAAI,gBAAgB,CAAC,GAAG,CAAC,SAAS,CAAC;gBAAE,OAAO,QAAQ,CAAC,OAAO,CAAC,OAAO,EAAE,QAAQ,CAAC,CAAC;YAChF,IAAI,iBAAiB,CAAC,GAAG,CAAC,SAAS,CAAC;gBAAE,OAAO,aAAa,CAAC,OAAO,CAAC,OAAO,EAAE,QAAQ,CAAC,CAAC;YACtF,OAAO,MAAM,CAAC,0BAA0B,SAAS,IAAI,0BAA0B,EAAE,EAAE;gBACjF,OAAO,EAAE,cAAc;gBACvB,IAAI,EAAE,IAAI;aACX,CAAC,CAAC;QACL,CAAC;KACF,CAAC;AACJ,CAAC;AAED,KAAK,UAAU,aAAa,CAC1B,OAAe,EACf,QAA4B;IAE5B,MAAM,OAAO,GAAG,MAAM,eAAe,CAAC,CAAC,aAAa,CAAC,EAAE,QAAQ,CAAC,CAAC;IACjE,IAAI,OAAO,CAAC,MAAM,GAAG,CAAC;QAAE,OAAO,iBAAiB,CAAC,wCAAwC,EAAE,OAAO,CAAC,CAAC;IAEpG,MAAM,SAAS,GAAG,MAAM,QAAQ,CAAC,WAAW,EAAE,CAAC;IAC/C,IAAI,CAAC;QACH,MAAM,QAAQ,CAAC,GAAG,CAAC,aAAa,EAAE;YAChC,yBAAyB,aAAa,CAAC,IAAI,CAAC,IAAI,CAAC,SAAS,EAAE,SAAS,CAAC,CAAC,CAAC,IAAI,EAAE;YAC9E,YAAY;YACZ,cAAc;YACd,UAAU;YACV,UAAU;YACV,SAAS;YACT,OAAO;SACR,CAAC,CAAC;QACH,MAAM,MAAM,GAAG,IAAI,CAAC,IAAI,CAAC,SAAS,EAAE,GAAG,IAAI,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,IAAI,MAAM,CAAC,CAAC;QACvE,MAAM,IAAI,GAAG,CAAC,MAAM,QAAQ,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC;QACtD,OAAO,IAAI;YACT,CAAC,CAAC;gBACE,IAAI;gBACJ,KAAK,EAAE,IAAI;gBACX,GAAG,EAAE,KAAK;gBACV,UAAU,EAAE,IAAI;gBAChB,UAAU,EAAE,EAAE,OAAO,EAAE,cAAc,EAAE,IAAI,EAAE,aAAa,EAAE;gBAC5D,SAAS,EAAE,aAAa;gBACxB,WAAW,EAAE,IAAI;aAClB;YACH,CAAC,CAAC,MAAM,CAAC,2BAA2B,EAAE,EAAE,OAAO,EAAE,cAAc,EAAE,IAAI,EAAE,aAAa,EAAE,CAAC,CAAC;IAC5F,CAAC;IAAC,OAAO,KAAK,EAAE,CAAC;QACf,OAAO,MAAM,CAAC,wCAAwC,YAAY,CAAC,KAAK,CAAC,EAAE,EAAE;YAC3E,OAAO,EAAE,cAAc;YACvB,IAAI,EAAE,aAAa;SACpB,CAAC,CAAC;IACL,CAAC;YAAS,CAAC;QACT,MAAM,QAAQ,CAAC,aAAa,CAAC,SAAS,CAAC,CAAC;IAC1C,CAAC;AACH,CAAC;AAED,KAAK,UAAU,UAAU,CACvB,OAAe,EACf,WAAmB,EACnB,QAA4B;IAE5B,MAAM,OAAO,GAAG,MAAM,eAAe,CAAC,CAAC,SAAS,EAAE,WAAW,CAAC,EAAE,QAAQ,CAAC,CAAC;IAC1E,IAAI,OAAO,CAAC,MAAM,GAAG,CAAC;QAAE,OAAO,iBAAiB,CAAC,uCAAuC,EAAE,OAAO,CAAC,CAAC;IAEnG,IAAI,IAAY,CAAC;IACjB,IAAI,CAAC;QACH,CAAC,EAAE,MAAM,EAAE,IAAI,EAAE,GAAG,MAAM,QAAQ,CAAC,GAAG,CAAC,SAAS,EAAE,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC;IAChE,CAAC;IAAC,OAAO,KAAK,EAAE,CAAC;QACf,OAAO,MAAM,CAAC,sCAAsC,YAAY,CAAC,KAAK,CAAC,EAAE,EAAE;YACzE,OAAO,EAAE,cAAc;YACvB,IAAI,EAAE,SAAS;SAChB,CAAC,CAAC;IACL,CAAC;IAED,MAAM,KAAK,GAAG,MAAM,CAAC,sBAAsB,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC;IAClE,IAAI,KAAK,GAAG,CAAC,EAAE,CAAC;QACd,OAAO,MAAM,CAAC,8CAA8C,EAAE;YAC5D,OAAO,EAAE,cAAc;YACvB,IAAI,EAAE,SAAS;SAChB,CAAC,CAAC;IACL,CAAC;IAED,IAAI,MAAc,CAAC;IACnB,IAAI,CAAC;QACH,CAAC,EAAE,MAAM,EAAE,GAAG,MAAM,QAAQ,CAAC,GAAG,CAAC,WAAW,EAAE,CAAC,SAAS,EAAE,OAAO,EAAE,GAAG,CAAC,CAAC,CAAC,CAAC;IAC5E,CAAC;IAAC,OAAO,KAAK,EAAE,CAAC;QACf,OAAO,MAAM,CAAC,qCAAqC,YAAY,CAAC,KAAK,CAAC,EAAE,EAAE;YACxE,OAAO,EAAE,cAAc;YACvB,IAAI,EAAE,WAAW;SAClB,CAAC,CAAC;IACL,CAAC;IACD,MAAM,QAAQ,GAAG,MAAM,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;IACpC,iFAAiF;IACjF,gFAAgF;IAChF,MAAM,WAAW,GAAG,KAAK,CAAC,IAAI,CAAC,EAAE,MAAM,EAAE,KAAK,EAAE,EAAE,CAAC,CAAC,EAAE,KAAK,EAAE,EAAE,CAAC,CAAC;QAC/D,IAAI,EAAE,KAAK,GAAG,CAAC;QACf,IAAI,EAAE,CAAC,QAAQ,CAAC,KAAK,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE;KACrC,CAAC,CAAC,CAAC;IACJ,MAAM,QAAQ,GAAG,WAAW,CAAC,MAAM,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,OAAO,CAAC,IAAI,CAAC,MAAM,IAAI,8BAA8B,CAAC,CAAC;IACxG,MAAM,eAAe,GAAG,WAAW;SAChC,MAAM,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,OAAO,CAAC,IAAI,CAAC,MAAM,GAAG,8BAA8B,CAAC;SACzE,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC;IAElC,IAAI,eAAe,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QAC/B,OAAO,MAAM,CAAC,OAAO,EAAE,KAAK,EAAE,eAAe,EAAE,QAAQ,EAAE,WAAW,EAAE,QAAQ,CAAC,CAAC;IAClF,CAAC;IAED,MAAM,IAAI,GAAG,QAAQ,CAAC,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;IAElE,OAAO;QACL,IAAI;QACJ,KAAK,EAAE,EAAE,KAAK,EAAE,QAAQ,EAAE;QAC1B,GAAG,EAAE,KAAK;QACV,UAAU,EAAE,IAAI;QAChB,UAAU,EAAE,EAAE,OAAO,EAAE,cAAc,EAAE,IAAI,EAAE,WAAW,EAAE;QAC1D,SAAS,EAAE,YAAY;QACvB,WAAW,EAAE,IAAI;KAClB,CAAC;AACJ,CAAC;AAED,KAAK,UAAU,QAAQ,CAAC,OAAe,EAAE,QAA4B;IACnE,MAAM,OAAO,GAAG,MAAM,eAAe,CAAC,CAAC,WAAW,CAAC,EAAE,QAAQ,CAAC,CAAC;IAC/D,IAAI,OAAO,CAAC,MAAM,GAAG,CAAC;QAAE,OAAO,iBAAiB,CAAC,8BAA8B,EAAE,OAAO,CAAC,CAAC;IAE1F,IAAI,CAAC;QACH,MAAM,EAAE,MAAM,EAAE,GAAG,MAAM,QAAQ,CAAC,GAAG,CAAC,WAAW,EAAE,CAAC,OAAO,EAAE,QAAQ,EAAE,KAAK,CAAC,CAAC,CAAC;QAC/E,MAAM,UAAU,GAAG,iBAAiB,CAAC,MAAM,CAAC,CAAC;QAC7C,OAAO;YACL,IAAI,EAAE,UAAU,CAAC,IAAI;YACrB,KAAK,EAAE;gBACL,KAAK,EAAE,CAAC;gBACR,QAAQ,EAAE,UAAU,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,EAAE,IAAI,EAAE,CAAC,EAAE,IAAI,EAAE,UAAU,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,CAAC,EAAE;aACtE;YACD,GAAG,EAAE,IAAI;YACT,UAAU,EAAE,cAAc,CAAC,UAAU,CAAC,WAAW,CAAC;YAClD,UAAU,EAAE,EAAE,OAAO,EAAE,cAAc,EAAE,IAAI,EAAE,WAAW,EAAE;YAC1D,SAAS,EAAE,KAAK;YAChB,WAAW,EAAE,IAAI;SAClB,CAAC;IACJ,CAAC;IAAC,OAAO,KAAK,EAAE,CAAC;QACf,OAAO,MAAM,CAAC,sCAAsC,YAAY,CAAC,KAAK,CAAC,EAAE,EAAE;YACzE,OAAO,EAAE,cAAc;YACvB,IAAI,EAAE,WAAW;SAClB,CAAC,CAAC;IACL,CAAC;AACH,CAAC;AAED,KAAK,UAAU,MAAM,CACnB,OAAe,EACf,SAAiB,EACjB,eAAyB,EACzB,iBAAmD,EACnD,WAAmB,EACnB,QAA4B;IAE5B,MAAM,OAAO,GAAG,MAAM,eAAe,CAAC,CAAC,UAAU,EAAE,WAAW,CAAC,EAAE,QAAQ,CAAC,CAAC;IAC3E,IAAI,OAAO,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QACvB,MAAM,MAAM,GAAG,iBAAiB,CAAC,iDAAiD,EAAE,OAAO,CAAC,CAAC;QAC7F,IAAI,iBAAiB,CAAC,MAAM,KAAK,CAAC;YAAE,OAAO,MAAM,CAAC;QAClD,OAAO;YACL,GAAG,MAAM;YACT,IAAI,EAAE,iBAAiB,CAAC,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC,IAAI,CAAC,MAAM,CAAC;YACnE,KAAK,EAAE,EAAE,KAAK,EAAE,SAAS,EAAE,QAAQ,EAAE,iBAAiB,EAAE;YACxD,UAAU,EAAE,EAAE,OAAO,EAAE,cAAc,EAAE,IAAI,EAAE,WAAW,EAAE;YAC1D,SAAS,EAAE,YAAY;SACxB,CAAC;IACJ,CAAC;IAED,MAAM,SAAS,GAAG,MAAM,QAAQ,CAAC,WAAW,EAAE,CAAC;IAC/C,MAAM,WAAW,GAAG,eAAe,CAAC,KAAK,CAAC,CAAC,EAAE,IAAI,CAAC,GAAG,CAAC,CAAC,EAAE,WAAW,CAAC,CAAC,CAAC;IACvE,MAAM,QAAQ,GAAG,CAAC,GAAG,iBAAiB,CAAC,CAAC;IACxC,MAAM,WAAW,GAAa,EAAE,CAAC;IACjC,IAAI,YAAY,GAAG,CAAC,CAAC;IACrB,IAAI,IAAI,GAA6B,UAAU,CAAC;IAChD,IAAI,CAAC;QACH,KAAK,MAAM,IAAI,IAAI,WAAW,EAAE,CAAC;YAC/B,MAAM,MAAM,GAAG,IAAI,CAAC,IAAI,CAAC,SAAS,EAAE,QAAQ,IAAI,EAAE,CAAC,CAAC;YACpD,IAAI,GAAG,UAAU,CAAC;YAClB,MAAM,QAAQ,CAAC,GAAG,CAAC,UAAU,EAAE;gBAC7B,IAAI;gBACJ,MAAM,CAAC,IAAI,CAAC;gBACZ,IAAI;gBACJ,MAAM,CAAC,IAAI,CAAC;gBACZ,aAAa;gBACb,MAAM;gBACN,IAAI;gBACJ,KAAK;gBACL,OAAO;gBACP,MAAM;aACP,CAAC,CAAC;YACH,IAAI,GAAG,WAAW,CAAC;YACnB,MAAM,EAAE,MAAM,EAAE,GAAG,MAAM,QAAQ,CAAC,GAAG,CAAC,WAAW,EAAE,CAAC,GAAG,MAAM,MAAM,EAAE,QAAQ,EAAE,KAAK,CAAC,CAAC,CAAC;YACvF,MAAM,UAAU,GAAG,iBAAiB,CAAC,MAAM,CAAC,CAAC;YAC7C,IAAI,UAAU,CAAC,IAAI;gBAAE,QAAQ,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,IAAI,EAAE,UAAU,CAAC,IAAI,EAAE,CAAC,CAAC;YACpE,WAAW,CAAC,IAAI,CAAC,GAAG,UAAU,CAAC,WAAW,CAAC,CAAC;YAC5C,YAAY,IAAI,CAAC,CAAC;QACpB,CAAC;IACH,CAAC;IAAC,OAAO,KAAK,EAAE,CAAC;QACf,IAAI,QAAQ,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YACxB,MAAM,OAAO,GAAG,QAAQ,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,KAAK,EAAE,EAAE,CAAC,IAAI,CAAC,IAAI,GAAG,KAAK,CAAC,IAAI,CAAC,CAAC;YACvE,OAAO;gBACL,IAAI,EAAE,OAAO,CAAC,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC,IAAI,CAAC,MAAM,CAAC;gBACzD,KAAK,EAAE,EAAE,KAAK,EAAE,SAAS,EAAE,QAAQ,EAAE,OAAO,EAAE;gBAC9C,GAAG,EAAE,YAAY,GAAG,CAAC;gBACrB,UAAU,EAAE,cAAc,CAAC,WAAW,CAAC;gBACvC,UAAU,EAAE,EAAE,OAAO,EAAE,cAAc,EAAE,IAAI,EAAE;gBAC7C,SAAS,EAAE,YAAY,GAAG,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,YAAY;gBAClD,WAAW,EAAE;oBACX,IAAI,EAAE,oBAAoB;oBAC1B,OAAO,EAAE,+BAA+B,WAAW,CAAC,YAAY,CAAC,kBAAkB,QAAQ,CAAC,MAAM,OAAO,SAAS,WAAW,YAAY,CAAC,KAAK,CAAC,EAAE;oBAClJ,UAAU,EAAE,QAAQ,CAAC,MAAM;oBAC3B,WAAW,EAAE,SAAS;iBACvB;aACF,CAAC;QACJ,CAAC;QACD,OAAO,MAAM,CAAC,2BAA2B,YAAY,CAAC,KAAK,CAAC,EAAE,EAAE;YAC9D,OAAO,EAAE,cAAc;YACvB,IAAI;SACL,CAAC,CAAC;IACL,CAAC;YAAS,CAAC;QACT,MAAM,QAAQ,CAAC,aAAa,CAAC,SAAS,CAAC,CAAC;IAC1C,CAAC;IAED,MAAM,OAAO,GAAG,QAAQ,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,KAAK,EAAE,EAAE,CAAC,IAAI,CAAC,IAAI,GAAG,KAAK,CAAC,IAAI,CAAC,CAAC;IACvE,MAAM,IAAI,GAAG,OAAO,CAAC,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;IACjE,OAAO;QACL,IAAI;QACJ,KAAK,EAAE,EAAE,KAAK,EAAE,SAAS,EAAE,QAAQ,EAAE,OAAO,EAAE;QAC9C,GAAG,EAAE,IAAI;QACT,UAAU,EAAE,cAAc,CAAC,WAAW,CAAC;QACvC,UAAU,EAAE,EAAE,OAAO,EAAE,cAAc,EAAE,IAAI,EAAE,WAAW,EAAE;QAC1D,SAAS,EAAE,KAAK;QAChB,WAAW,EACT,WAAW,CAAC,MAAM,GAAG,eAAe,CAAC,MAAM;YACzC,CAAC,CAAC;gBACE,IAAI,EAAE,oBAAoB;gBAC1B,OAAO,EAAE,+BAA+B,QAAQ,CAAC,MAAM,OAAO,SAAS,QAAQ;gBAC/E,UAAU,EAAE,QAAQ,CAAC,MAAM;gBAC3B,WAAW,EAAE,SAAS;aACvB;YACH,CAAC,CAAC,IAAI;KACX,CAAC;AACJ,CAAC;AAED,SAAS,iBAAiB,CAAC,GAAW;IACpC,MAAM,KAAK,GAAG,IAAI,GAAG,EAAoB,CAAC;IAC1C,MAAM,WAAW,GAAa,EAAE,CAAC;IACjC,KAAK,MAAM,GAAG,IAAI,GAAG,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,CAAC;QAC9C,MAAM,MAAM,GAAG,GAAG,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;QAC/B,IAAI,MAAM,CAAC,CAAC,CAAC,KAAK,GAAG;YAAE,SAAS;QAChC,MAAM,IAAI,GAAG,MAAM,CAAC,KAAK,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,CAAC;QAChD,IAAI,CAAC,IAAI;YAAE,SAAS;QACpB,MAAM,IAAI,GAAG,MAAM,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;QAC1C,MAAM,KAAK,GAAG,KAAK,CAAC,GAAG,CAAC,IAAI,CAAC,IAAI,EAAE,CAAC;QACpC,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QACjB,KAAK,CAAC,GAAG,CAAC,IAAI,EAAE,KAAK,CAAC,CAAC;QACvB,MAAM,UAAU,GAAG,MAAM,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC,CAAC;QACtC,IAAI,MAAM,CAAC,QAAQ,CAAC,UAAU,CAAC,IAAI,UAAU,IAAI,CAAC;YAAE,WAAW,CAAC,IAAI,CAAC,UAAU,CAAC,CAAC;IACnF,CAAC;IACD,OAAO,EAAE,IAAI,EAAE,CAAC,GAAG,KAAK,CAAC,MAAM,EAAE,CAAC,CAAC,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,WAAW,EAAE,CAAC;AAC/F,CAAC;AAED,SAAS,cAAc,CAAC,WAAqB;IAC3C,OAAO,WAAW,CAAC,MAAM,GAAG,CAAC;QAC3B,CAAC,CAAC,WAAW,CAAC,MAAM,CAAC,CAAC,KAAK,EAAE,UAAU,EAAE,EAAE,CAAC,KAAK,GAAG,UAAU,EAAE,CAAC,CAAC,GAAG,WAAW,CAAC,MAAM,GAAG,GAAG;QAC7F,CAAC,CAAC,IAAI,CAAC;AACX,CAAC;AAED,KAAK,UAAU,eAAe,CAAC,eAAyB,EAAE,QAA4B;IACpF,MAAM,SAAS,GAAG,MAAM,OAAO,CAAC,GAAG,CAAC,eAAe,CAAC,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,QAAQ,CAAC,SAAS,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC;IACnG,OAAO,eAAe,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,KAAK,EAAE,EAAE,CAAC,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC,CAAC;AACjE,CAAC;AAED,SAAS,iBAAiB,CAAC,OAAe,EAAE,KAAe;IACzD,OAAO;QACL,IAAI,EAAE,EAAE;QACR,KAAK,EAAE,IAAI;QACX,GAAG,EAAE,KAAK;QACV,UAAU,EAAE,IAAI;QAChB,UAAU,EAAE,EAAE,OAAO,EAAE,cAAc,EAAE,IAAI,EAAE,IAAI,EAAE;QACnD,SAAS,EAAE,MAAM;QACjB,WAAW,EAAE,EAAE,IAAI,EAAE,oBAAoB,EAAE,OAAO,EAAE,GAAG,OAAO,KAAK,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,EAAE,KAAK,EAAE;KAC/F,CAAC;AACJ,CAAC;AAED,SAAS,YAAY,CAAC,KAAc;IAClC,OAAO,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC;AAChE,CAAC;AAED,SAAS,MAAM,CAAC,OAAe,EAAE,UAAgC;IAC/D,OAAO;QACL,IAAI,EAAE,EAAE;QACR,KAAK,EAAE,IAAI;QACX,GAAG,EAAE,KAAK;QACV,UAAU,EAAE,IAAI;QAChB,UAAU;QACV,SAAS,EAAE,MAAM;QACjB,WAAW,EAAE,EAAE,IAAI,EAAE,mBAAmB,EAAE,OAAO,EAAE;KACpD,CAAC;AACJ,CAAC"}
|
|
@@ -0,0 +1,4 @@
|
|
|
1
|
+
import type { Line } from '@tenphi/akno-protocol';
|
|
2
|
+
/** Attach persisted memory semantics to the visible payload line that follows a marker. */
|
|
3
|
+
export declare function qualifyManagedMemoryLines<T extends Line>(lines: T[], fileLines: string[]): T[];
|
|
4
|
+
//# sourceMappingURL=managed-lines.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"managed-lines.d.ts","sourceRoot":"","sources":["../../src/kb/managed-lines.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,IAAI,EAAuB,MAAM,uBAAuB,CAAC;AAQvE,2FAA2F;AAC3F,wBAAgB,yBAAyB,CAAC,CAAC,SAAS,IAAI,EAAE,KAAK,EAAE,CAAC,EAAE,EAAE,SAAS,EAAE,MAAM,EAAE,GAAG,CAAC,EAAE,CAc9F"}
|
|
@@ -0,0 +1,37 @@
|
|
|
1
|
+
import { aknoItemId } from "./page.js";
|
|
2
|
+
import { managedMemoryAnswerEligible, parseManagedMemoryMarker, } from "../write/managed-memory.js";
|
|
3
|
+
/** Attach persisted memory semantics to the visible payload line that follows a marker. */
|
|
4
|
+
export function qualifyManagedMemoryLines(lines, fileLines) {
|
|
5
|
+
return lines.map((line) => {
|
|
6
|
+
const markerLine = fileLines[line.n - 2];
|
|
7
|
+
if (markerLine === undefined)
|
|
8
|
+
return line;
|
|
9
|
+
const markerId = aknoItemId(markerLine);
|
|
10
|
+
if (!markerId)
|
|
11
|
+
return line;
|
|
12
|
+
const marker = parseManagedMemoryMarker(markerLine);
|
|
13
|
+
return {
|
|
14
|
+
...line,
|
|
15
|
+
memory: marker
|
|
16
|
+
? qualificationFor(marker)
|
|
17
|
+
: { status: 'unavailable', id: markerId, answer_eligible: false },
|
|
18
|
+
};
|
|
19
|
+
});
|
|
20
|
+
}
|
|
21
|
+
function qualificationFor(marker) {
|
|
22
|
+
return {
|
|
23
|
+
status: 'qualified',
|
|
24
|
+
id: marker.id,
|
|
25
|
+
level: 1,
|
|
26
|
+
kind: marker.kind,
|
|
27
|
+
subject: marker.subject,
|
|
28
|
+
source_role: marker.sourceRole,
|
|
29
|
+
...(marker.speaker ? { source_speaker: marker.speaker } : {}),
|
|
30
|
+
commitment: marker.commitment,
|
|
31
|
+
disposition: marker.disposition,
|
|
32
|
+
polarity: marker.polarity,
|
|
33
|
+
basis: marker.basis,
|
|
34
|
+
answer_eligible: managedMemoryAnswerEligible(marker),
|
|
35
|
+
};
|
|
36
|
+
}
|
|
37
|
+
//# sourceMappingURL=managed-lines.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"managed-lines.js","sourceRoot":"","sources":["../../src/kb/managed-lines.ts"],"names":[],"mappings":"AACA,OAAO,EAAE,UAAU,EAAE,MAAM,WAAW,CAAC;AACvC,OAAO,EACL,2BAA2B,EAC3B,wBAAwB,GAEzB,MAAM,4BAA4B,CAAC;AAEpC,2FAA2F;AAC3F,MAAM,UAAU,yBAAyB,CAAiB,KAAU,EAAE,SAAmB;IACvF,OAAO,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE;QACxB,MAAM,UAAU,GAAG,SAAS,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC;QACzC,IAAI,UAAU,KAAK,SAAS;YAAE,OAAO,IAAI,CAAC;QAC1C,MAAM,QAAQ,GAAG,UAAU,CAAC,UAAU,CAAC,CAAC;QACxC,IAAI,CAAC,QAAQ;YAAE,OAAO,IAAI,CAAC;QAC3B,MAAM,MAAM,GAAG,wBAAwB,CAAC,UAAU,CAAC,CAAC;QACpD,OAAO;YACL,GAAG,IAAI;YACP,MAAM,EAAE,MAAM;gBACZ,CAAC,CAAC,gBAAgB,CAAC,MAAM,CAAC;gBAC1B,CAAC,CAAC,EAAE,MAAM,EAAE,aAAa,EAAE,EAAE,EAAE,QAAQ,EAAE,eAAe,EAAE,KAAK,EAAE;SACpE,CAAC;IACJ,CAAC,CAAC,CAAC;AACL,CAAC;AAED,SAAS,gBAAgB,CAAC,MAA2B;IACnD,OAAO;QACL,MAAM,EAAE,WAAW;QACnB,EAAE,EAAE,MAAM,CAAC,EAAE;QACb,KAAK,EAAE,CAAC;QACR,IAAI,EAAE,MAAM,CAAC,IAAI;QACjB,OAAO,EAAE,MAAM,CAAC,OAAO;QACvB,WAAW,EAAE,MAAM,CAAC,UAAU;QAC9B,GAAG,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC,CAAC,EAAE,cAAc,EAAE,MAAM,CAAC,OAAO,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;QAC7D,UAAU,EAAE,MAAM,CAAC,UAAU;QAC7B,WAAW,EAAE,MAAM,CAAC,WAAW;QAC/B,QAAQ,EAAE,MAAM,CAAC,QAAQ;QACzB,KAAK,EAAE,MAAM,CAAC,KAAK;QACnB,eAAe,EAAE,2BAA2B,CAAC,MAAM,CAAC;KACrD,CAAC;AACJ,CAAC"}
|
|
@@ -69,9 +69,9 @@ export declare const VERIFY_SCHEMA: z.ZodObject<{
|
|
|
69
69
|
outcome: z.ZodEnum<{
|
|
70
70
|
unresolved: "unresolved";
|
|
71
71
|
superseded: "superseded";
|
|
72
|
+
qualified: "qualified";
|
|
72
73
|
not_a_conflict: "not_a_conflict";
|
|
73
74
|
time_scoped: "time_scoped";
|
|
74
|
-
qualified: "qualified";
|
|
75
75
|
}>;
|
|
76
76
|
current: z.ZodNullable<z.ZodString>;
|
|
77
77
|
qualification: z.ZodNullable<z.ZodObject<{
|
package/dist/open.d.ts
CHANGED
|
@@ -34,7 +34,7 @@ export interface OpenOptions extends LoadOptions {
|
|
|
34
34
|
* it at zero — they should say so immediately rather than hang.
|
|
35
35
|
*/
|
|
36
36
|
writeLockWaitMs?: number;
|
|
37
|
-
/** Start the
|
|
37
|
+
/** Start the native filesystem watcher and periodic sweep. Off for one-shot commands. */
|
|
38
38
|
watch?: boolean;
|
|
39
39
|
watchEvents?: AknoWatchEvents;
|
|
40
40
|
/**
|
package/dist/open.d.ts.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"open.d.ts","sourceRoot":"","sources":["../src/open.ts"],"names":[],"mappings":"AAEA,OAAO,EAGL,KAAK,OAAO,EACZ,KAAK,MAAM,EACX,KAAK,OAAO,EACZ,KAAK,QAAQ,EACd,MAAM,uBAAuB,CAAC;AAC/B,OAAO,EAAc,KAAK,WAAW,EAAE,MAAM,kBAAkB,CAAC;AAChE,OAAO,KAAK,EAAE,UAAU,EAAE,MAAM,oBAAoB,CAAC;AAMrD,OAAO,EAAW,KAAK,YAAY,EAAE,KAAK,WAAW,EAAE,MAAM,oBAAoB,CAAC;AAClF,OAAO,EAAW,KAAK,aAAa,EAAE,MAAM,oBAAoB,CAAC;AACjE,OAAO,EAAU,KAAK,aAAa,EAAE,KAAK,YAAY,EAAE,MAAM,aAAa,CAAC;AAI5E,OAAO,EAAW,KAAK,aAAa,EAAE,MAAM,oBAAoB,CAAC;AACjE,OAAO,EAAQ,KAAK,WAAW,EAAE,MAAM,iBAAiB,CAAC;AAiBzD,OAAO,EAA2B,KAAK,WAAW,EAAE,MAAM,mBAAmB,CAAC;AAC9E,OAAO,EAAS,KAAK,YAAY,EAAE,KAAK,WAAW,EAAE,MAAM,wBAAwB,CAAC;AACpF,OAAO,EAUL,KAAK,sBAAsB,EAC3B,KAAK,wBAAwB,EAC7B,KAAK,eAAe,EACpB,KAAK,qBAAqB,EAC1B,KAAK,sBAAsB,EAC3B,KAAK,0BAA0B,EAC/B,KAAK,wBAAwB,EAC7B,KAAK,eAAe,EACpB,KAAK,iBAAiB,EACtB,KAAK,sBAAsB,EAC5B,MAAM,wBAAwB,CAAC;AAEhC,OAAO,EAA0B,KAAK,qBAAqB,EAAE,MAAM,8BAA8B,CAAC;AAClG,OAAO,EAEL,KAAK,wBAAwB,EAC7B,KAAK,yBAAyB,EAC/B,MAAM,2BAA2B,CAAC;AACnC,OAAO,EAEL,KAAK,qBAAqB,EAC1B,KAAK,oBAAoB,EAC1B,MAAM,kCAAkC,CAAC;AAE1C,oFAAoF;AACpF,MAAM,WAAW,eAAgB,SAAQ,aAAa;IACpD,OAAO,CAAC,EAAE,CAAC,MAAM,EAAE,WAAW,KAAK,IAAI,CAAC;CACzC;AAED,MAAM,WAAW,WAAY,SAAQ,WAAW;IAC9C;;;;OAIG;IACH,KAAK,CAAC,EAAE,MAAM,GAAG,OAAO,GAAG,MAAM,CAAC;IAClC,yEAAyE;IACzE,QAAQ,CAAC,EAAE,OAAO,CAAC;IACnB;;;;;;;OAOG;IACH,eAAe,CAAC,EAAE,MAAM,CAAC;IACzB,
|
|
1
|
+
{"version":3,"file":"open.d.ts","sourceRoot":"","sources":["../src/open.ts"],"names":[],"mappings":"AAEA,OAAO,EAGL,KAAK,OAAO,EACZ,KAAK,MAAM,EACX,KAAK,OAAO,EACZ,KAAK,QAAQ,EACd,MAAM,uBAAuB,CAAC;AAC/B,OAAO,EAAc,KAAK,WAAW,EAAE,MAAM,kBAAkB,CAAC;AAChE,OAAO,KAAK,EAAE,UAAU,EAAE,MAAM,oBAAoB,CAAC;AAMrD,OAAO,EAAW,KAAK,YAAY,EAAE,KAAK,WAAW,EAAE,MAAM,oBAAoB,CAAC;AAClF,OAAO,EAAW,KAAK,aAAa,EAAE,MAAM,oBAAoB,CAAC;AACjE,OAAO,EAAU,KAAK,aAAa,EAAE,KAAK,YAAY,EAAE,MAAM,aAAa,CAAC;AAI5E,OAAO,EAAW,KAAK,aAAa,EAAE,MAAM,oBAAoB,CAAC;AACjE,OAAO,EAAQ,KAAK,WAAW,EAAE,MAAM,iBAAiB,CAAC;AAiBzD,OAAO,EAA2B,KAAK,WAAW,EAAE,MAAM,mBAAmB,CAAC;AAC9E,OAAO,EAAS,KAAK,YAAY,EAAE,KAAK,WAAW,EAAE,MAAM,wBAAwB,CAAC;AACpF,OAAO,EAUL,KAAK,sBAAsB,EAC3B,KAAK,wBAAwB,EAC7B,KAAK,eAAe,EACpB,KAAK,qBAAqB,EAC1B,KAAK,sBAAsB,EAC3B,KAAK,0BAA0B,EAC/B,KAAK,wBAAwB,EAC7B,KAAK,eAAe,EACpB,KAAK,iBAAiB,EACtB,KAAK,sBAAsB,EAC5B,MAAM,wBAAwB,CAAC;AAEhC,OAAO,EAA0B,KAAK,qBAAqB,EAAE,MAAM,8BAA8B,CAAC;AAClG,OAAO,EAEL,KAAK,wBAAwB,EAC7B,KAAK,yBAAyB,EAC/B,MAAM,2BAA2B,CAAC;AACnC,OAAO,EAEL,KAAK,qBAAqB,EAC1B,KAAK,oBAAoB,EAC1B,MAAM,kCAAkC,CAAC;AAE1C,oFAAoF;AACpF,MAAM,WAAW,eAAgB,SAAQ,aAAa;IACpD,OAAO,CAAC,EAAE,CAAC,MAAM,EAAE,WAAW,KAAK,IAAI,CAAC;CACzC;AAED,MAAM,WAAW,WAAY,SAAQ,WAAW;IAC9C;;;;OAIG;IACH,KAAK,CAAC,EAAE,MAAM,GAAG,OAAO,GAAG,MAAM,CAAC;IAClC,yEAAyE;IACzE,QAAQ,CAAC,EAAE,OAAO,CAAC;IACnB;;;;;;;OAOG;IACH,eAAe,CAAC,EAAE,MAAM,CAAC;IACzB,yFAAyF;IACzF,KAAK,CAAC,EAAE,OAAO,CAAC;IAChB,WAAW,CAAC,EAAE,eAAe,CAAC;IAC9B;;;OAGG;IACH,mBAAmB,CAAC,EAAE,OAAO,CAAC;IAC9B,4EAA4E;IAC5E,mBAAmB,CAAC,EAAE,OAAO,CAAC;CAC/B;AAED,MAAM,WAAW,IAAK,SAAQ,OAAO;IACnC,QAAQ,CAAC,MAAM,EAAE,UAAU,CAAC;IAC5B,QAAQ,CAAC,QAAQ,EAAE,OAAO,CAAC;IAC3B,uDAAuD;IACvD,QAAQ,CAAC,UAAU,EAAE,MAAM,GAAG,IAAI,CAAC;IACnC,sDAAsD;IACtD,KAAK,CAAC,OAAO,CAAC,EAAE,YAAY,GAAG,OAAO,CAAC,WAAW,CAAC,CAAC;IACpD,MAAM,CAAC,OAAO,CAAC,EAAE,aAAa,GAAG,OAAO,CAAC,YAAY,CAAC,CAAC;IACvD,kDAAkD;IAClD,KAAK,CAAC,IAAI,EAAE,MAAM,GAAG;QAAE,SAAS,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;QAAC,UAAU,EAAE;YAAE,IAAI,EAAE,MAAM,CAAC;YAAC,MAAM,EAAE,MAAM,CAAA;SAAE,EAAE,CAAA;KAAE,CAAC;IAC5G,6EAA6E;IAC7E,iBAAiB,CAAC,IAAI,EAAE,MAAM,EAAE,IAAI,CAAC,EAAE,eAAe,GAAG,qBAAqB,CAAC;IAC/E,kEAAkE;IAClE,OAAO,CAAC,KAAK,CAAC,EAAE,MAAM,GAAG,aAAa,EAAE,CAAC;IACzC,2CAA2C;IAC3C,SAAS,IAAI,WAAW,EAAE,CAAC;IAC3B,+CAA+C;IAC/C,KAAK,CAAC,KAAK,CAAC,EAAE,MAAM,EAAE,QAAQ,CAAC,EAAE,SAAS,qBAAqB,EAAE,GAAG,sBAAsB,EAAE,CAAC;IAC7F,qEAAqE;IACrE,IAAI,CAAC,MAAM,EAAE,MAAM,GAAG,eAAe,CAAC;IACtC,6DAA6D;IAC7D,eAAe,CAAC,MAAM,EAAE,MAAM,EAAE,MAAM,CAAC,EAAE,MAAM,EAAE,QAAQ,CAAC,EAAE,MAAM,GAAG,MAAM,CAAC;IAC5E,oGAAoG;IACpG,UAAU,CAAC,MAAM,EAAE,MAAM,EAAE,MAAM,EAAE,MAAM,EAAE,KAAK,EAAE,wBAAwB,GAAG,OAAO,CAAC,eAAe,CAAC,CAAC;IACtG,mDAAmD;IACnD,UAAU,CACR,MAAM,EAAE,MAAM,EACd,MAAM,EAAE,MAAM,EACd,OAAO,EAAE,SAAS,GAAG,QAAQ,EAC7B,MAAM,CAAC,EAAE,MAAM,EACf,OAAO,CAAC,EAAE,wBAAwB,GACjC,eAAe,CAAC;IACnB,iFAAiF;IACjF,SAAS,CAAC,MAAM,EAAE,MAAM,EAAE,OAAO,CAAC,EAAE,wBAAwB,GAAG,OAAO,CAAC,sBAAsB,CAAC,CAAC;IAC/F,+EAA+E;IAC/E,aAAa,CAAC,MAAM,EAAE,MAAM,EAAE,MAAM,CAAC,EAAE,MAAM,GAAG,eAAe,CAAC;IAChE,qFAAqF;IACrF,UAAU,CAAC,OAAO,CAAC,EAAE;QAAE,KAAK,CAAC,EAAE,OAAO,CAAA;KAAE,GAAG,0BAA0B,CAAC;IACtE,yDAAyD;IACzD,iBAAiB,CAAC,KAAK,CAAC,EAAE,sBAAsB,GAAG,iBAAiB,CAAC;IACrE,wFAAwF;IACxF,iBAAiB,CAAC,KAAK,EAAE,wBAAwB,GAAG,yBAAyB,CAAC;IAC9E,wFAAwF;IACxF,YAAY,CAAC,OAAO,CAAC,EAAE,qBAAqB,GAAG,OAAO,CAAC,oBAAoB,CAAC,CAAC;IAC7E;;;;OAIG;IACH;;;;;;OAMG;IACH,OAAO,CACL,UAAU,EAAE,MAAM,EAClB,OAAO,CAAC,EAAE;QAAE,IAAI,CAAC,EAAE,MAAM,CAAA;KAAE,GAC1B,OAAO,CAAC;QAAE,OAAO,EAAE,MAAM,CAAC;QAAC,KAAK,CAAC,EAAE,QAAQ,CAAC,OAAO,CAAC,CAAC;QAAC,MAAM,CAAC,EAAE,QAAQ,CAAC,QAAQ,CAAC,CAAA;KAAE,CAAC,CAAC;IACxF,uEAAuE;IACvE,OAAO,CAAC,UAAU,EAAE,MAAM,GAAG,OAAO,CAAC;QAAE,OAAO,EAAE,MAAM,CAAA;KAAE,CAAC,CAAC;IAC1D;;;;;OAKG;IACH,KAAK,CAAC,OAAO,CAAC,EAAE;QAAE,KAAK,CAAC,EAAE,MAAM,CAAA;KAAE,GAAG,OAAO,CAAC,WAAW,CAAC,CAAC;IAC1D;;;;;;;OAOG;IACH,KAAK,CAAC,OAAO,CAAC,EAAE,YAAY,GAAG,OAAO,CAAC,WAAW,CAAC,CAAC;IACpD,0DAA0D;IAC1D,SAAS,IAAI,OAAO,CAAC,IAAI,CAAC,CAAC;IAC3B,iFAAiF;IACjF;;;OAGG;IACH,IAAI,CAAC,CAAC,SAAS,MAAM,EACnB,EAAE,EAAE,CAAC,EACL,KAAK,EAAE,OAAO,CAAC,CAAC,CAAC,EACjB,OAAO,CAAC,EAAE;QAAE,KAAK,CAAC,EAAE,MAAM,GAAG,OAAO,GAAG,MAAM,CAAA;KAAE,GAC9C,OAAO,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAC;IACxB,KAAK,IAAI,OAAO,CAAC,IAAI,CAAC,CAAC;CACxB;AAED;;;;GAIG;AACH,wBAAgB,mBAAmB,CACjC,MAAM,EAAE,WAAW,GAAG,MAAM,GAAG,YAAY,GAAG,IAAI,EAClD,SAAS,EAAE,MAAM,GAAG,IAAI,GACvB,MAAM,CAWR;AAED;;;;;;;;;;;GAWG;AACH,wBAAsB,IAAI,CAAC,OAAO,GAAE,WAAgB,GAAG,OAAO,CAAC,IAAI,CAAC,CAkWnE"}
|
package/dist/ops/answer.d.ts.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"answer.d.ts","sourceRoot":"","sources":["../../src/ops/answer.ts"],"names":[],"mappings":"AACA,OAAO,EAKL,KAAK,YAAY,EAGlB,MAAM,uBAAuB,CAAC;AAC/B,OAAO,KAAK,EAAE,WAAW,EAAE,MAAM,eAAe,CAAC;AACjD,OAAO,EAAE,KAAK,WAAW,EAAqB,KAAK,UAAU,EAAkB,MAAM,qBAAqB,CAAC;AAG3G,eAAO,MAAM,qBAAqB,yBAAyB,CAAC;AAC5D,eAAO,MAAM,8BAA8B,uBAAuB,CAAC;AAkCnE,MAAM,WAAW,qBAAqB;IACpC,MAAM,EAAE,IAAI,GAAG,QAAQ,GAAG,SAAS,CAAC;IACpC,SAAS,EAAE,MAAM,GAAG,IAAI,CAAC;IACzB,KAAK,EAAE,UAAU,GAAG,IAAI,CAAC;IACzB,KAAK,EAAE,MAAM,GAAG,IAAI,CAAC;CACtB;AAED,MAAM,WAAW,qBAAqB;IACpC,UAAU,EAAE,qBAAqB,CAAC;IAClC,YAAY,EAAE,qBAAqB,CAAC;CACrC;AA2BD;;;;;;GAMG;AACH,wBAAsB,MAAM,CAAC,GAAG,EAAE,WAAW,EAAE,QAAQ,EAAE,OAAO,GAAG,OAAO,CAAC,YAAY,CAAC,
|
|
1
|
+
{"version":3,"file":"answer.d.ts","sourceRoot":"","sources":["../../src/ops/answer.ts"],"names":[],"mappings":"AACA,OAAO,EAKL,KAAK,YAAY,EAGlB,MAAM,uBAAuB,CAAC;AAC/B,OAAO,KAAK,EAAE,WAAW,EAAE,MAAM,eAAe,CAAC;AACjD,OAAO,EAAE,KAAK,WAAW,EAAqB,KAAK,UAAU,EAAkB,MAAM,qBAAqB,CAAC;AAG3G,eAAO,MAAM,qBAAqB,yBAAyB,CAAC;AAC5D,eAAO,MAAM,8BAA8B,uBAAuB,CAAC;AAkCnE,MAAM,WAAW,qBAAqB;IACpC,MAAM,EAAE,IAAI,GAAG,QAAQ,GAAG,SAAS,CAAC;IACpC,SAAS,EAAE,MAAM,GAAG,IAAI,CAAC;IACzB,KAAK,EAAE,UAAU,GAAG,IAAI,CAAC;IACzB,KAAK,EAAE,MAAM,GAAG,IAAI,CAAC;CACtB;AAED,MAAM,WAAW,qBAAqB;IACpC,UAAU,EAAE,qBAAqB,CAAC;IAClC,YAAY,EAAE,qBAAqB,CAAC;CACrC;AA2BD;;;;;;GAMG;AACH,wBAAsB,MAAM,CAAC,GAAG,EAAE,WAAW,EAAE,QAAQ,EAAE,OAAO,GAAG,OAAO,CAAC,YAAY,CAAC,CAoNvF;AA0ED;;;GAGG;AACH,wBAAsB,gBAAgB,CAAC,KAAK,EAAE,WAAW,GAAG,OAAO,CAAC,qBAAqB,CAAC,CAwDzF"}
|
package/dist/ops/answer.js
CHANGED
|
@@ -119,6 +119,16 @@ export async function answer(ctx, rawInput) {
|
|
|
119
119
|
};
|
|
120
120
|
}
|
|
121
121
|
if (evidence.length === 0) {
|
|
122
|
+
const noncanonicalMemoryFound = recalled.results.some((result) => result.type === 'page' && result.lines.some((line) => line.memory?.answer_eligible === false));
|
|
123
|
+
if (noncanonicalMemoryFound) {
|
|
124
|
+
return {
|
|
125
|
+
status: recalled.status,
|
|
126
|
+
outcome: 'not_answered',
|
|
127
|
+
...base,
|
|
128
|
+
...(recalled.degraded ? { degraded: recalled.degraded } : {}),
|
|
129
|
+
note: 'related memory was found, but it was explicitly noncanonical and cannot ground a factual answer',
|
|
130
|
+
};
|
|
131
|
+
}
|
|
122
132
|
return {
|
|
123
133
|
status: 'degraded',
|
|
124
134
|
degraded: dedupeReasons([...(recalled.degraded ?? []), 'answer_failed']),
|
|
@@ -387,15 +397,17 @@ function buildEvidence(results) {
|
|
|
387
397
|
};
|
|
388
398
|
for (const result of results) {
|
|
389
399
|
if (result.type === 'page') {
|
|
390
|
-
|
|
400
|
+
const eligibleLines = result.lines.filter((line) => line.memory?.answer_eligible !== false && !/^\s*<!--/.test(line.text));
|
|
401
|
+
if (eligibleLines.length > 0) {
|
|
391
402
|
add(`page:${result.slug}`, {
|
|
392
403
|
type: 'page',
|
|
393
404
|
slug: result.slug,
|
|
394
405
|
title: result.title,
|
|
395
|
-
lines:
|
|
406
|
+
lines: eligibleLines.map((line) => ({
|
|
396
407
|
n: line.n,
|
|
397
408
|
text: line.text,
|
|
398
409
|
...(line.confidence !== undefined ? { confidence: line.confidence } : {}),
|
|
410
|
+
...(line.memory !== undefined ? { memory: line.memory } : {}),
|
|
399
411
|
})),
|
|
400
412
|
});
|
|
401
413
|
}
|