Press n or j to go to the next uncovered block, b, p or k for the previous block.
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 | /**
* Indexing Service
*
* This service is responsible for indexing code files and updating
* code entities in the database when files change.
*/
import path from "path";
import { promises as fs } from "fs";
import { v4 as uuidv4 } from "uuid";
import crypto from "crypto";
import parserService from "./parser.service.js";
import backgroundJobManager from "./job.service.js";
import dbQueries from "../db/queries.js";
import config from "../config.js";
import logger from "../utils/logger.js";
// File type configurations
const CODE_FILE_EXTENSIONS = {
javascript: [".js", ".jsx", ".mjs"],
typescript: [".ts", ".tsx"],
python: [".py"],
};
// Markdown file extensions
const MARKDOWN_FILE_EXTENSIONS = [".md", ".markdown", ".mdown", ".mdwn"];
// Text file extensions for content indexing (documentation, config files, etc.)
const TEXT_FILE_EXTENSIONS = [
".txt",
".json",
".yml",
".yaml",
".toml",
".ini",
".env",
".html",
".css",
".scss",
".less",
];
// File extensions to ignore
const IGNORED_FILE_EXTENSIONS = [
".jpg",
".jpeg",
".png",
".gif",
".bmp",
".ico",
".svg",
".pdf",
".zip",
".tar",
".gz",
".7z",
".rar",
".mp3",
".mp4",
".mov",
".avi",
".wmv",
".ttf",
".woff",
".woff2",
".eot",
".dll",
".exe",
".so",
".dylib",
".class",
".jar",
".war",
".ear",
".pyc",
".pyo",
".pyd",
];
/**
* IndexingService class
* Responsible for indexing code entities and processing file changes
*/
export class IndexingService {
/**
* Creates a new IndexingService instance
* @param {Object} options - Service dependencies
* @param {Object} options.dbClient - The database client
* @param {Object} [options.parserService] - The parser service instance
* @param {Object} [options.backgroundJobManager] - The background job manager instance
* @param {Object} [options.dbQueries] - Database queries module
*/
constructor({
dbClient,
parserService: customParserService = parserService,
backgroundJobManager: customJobManager = backgroundJobManager,
dbQueries: customDbQueries = dbQueries,
}) {
this.dbClient = dbClient;
this.parserService = customParserService;
this.jobManager = customJobManager;
this.dbQueries = customDbQueries;
this.initialized = false;
logger.info("IndexingService initialized");
}
/**
* Initialize the IndexingService
* @returns {Promise<void>}
*/
async initialize() {
try {
if (!this.initialized) {
logger.info("Initializing IndexingService");
// Initialize parser service if not already initialized
if (!this.parserService.initialized) {
await this.parserService.initialize(config.TREE_SITTER_LANGUAGES);
}
// Initialize job manager if not already initialized
if (!this.jobManager.initialized) {
await this.jobManager.initialize();
}
this.initialized = true;
logger.info("IndexingService initialized successfully");
}
} catch (error) {
logger.error(`Error initializing IndexingService: ${error.message}`, {
error,
});
throw error;
}
}
/**
* Determine the file type based on extension
* @param {string} filePath - Path to the file
* @returns {Object} File type information
*/
determineFileType(filePath) {
if (!filePath) return { type: "unknown", language: null };
const extension = path.extname(filePath).toLowerCase();
const fileName = path.basename(filePath).toLowerCase();
// Check if file should be ignored
if (IGNORED_FILE_EXTENSIONS.includes(extension)) {
return { type: "ignored", language: null };
}
// Check for Markdown files
if (MARKDOWN_FILE_EXTENSIONS.includes(extension)) {
return { type: "markdown", language: null };
}
// Check for code files
for (const [language, extensions] of Object.entries(CODE_FILE_EXTENSIONS)) {
if (extensions.includes(extension)) {
return { type: "code", language };
}
}
// Check for text files
if (TEXT_FILE_EXTENSIONS.includes(extension)) {
return { type: "text", language: null };
}
// Special handling for unknown files
if (extension === "") {
// Files without extension could be important config files
if (["dockerfile", "makefile", "jenkinsfile"].includes(fileName)) {
return { type: "text", language: null };
}
}
return { type: "unknown", language: null };
}
/**
* Check if a file is a Markdown document (case-insensitive)
* @param {string} filePath - Path to the file
* @returns {boolean} True if the file is a Markdown document
*/
isMarkdownFile(filePath) {
if (!filePath) return false;
const extension = path.extname(filePath).toLowerCase();
return MARKDOWN_FILE_EXTENSIONS.includes(extension);
}
/**
* Process a list of changed files
* @param {Array<Object>} changedFilesList - List of changed files with their statuses
* @param {string} changedFilesList[].filePath - Path to the changed file
* @param {string} changedFilesList[].status - Status of the change ('added' | 'modified' | 'deleted' | 'renamed')
* @param {string} [changedFilesList[].oldFilePath] - Previous path for renamed files
* @returns {Promise<Object>} Processing results
*/
async processFileChanges(changedFilesList) {
try {
if (!this.initialized) {
await this.initialize();
}
if (!changedFilesList || changedFilesList.length === 0) {
logger.info("No file changes to process");
return { processed: 0 };
}
logger.info(
`Starting to process ${changedFilesList.length} file changes`
);
// Group files by status
const grouped = {
added: [],
modified: [],
deleted: [],
renamed: [],
};
// First, categorize files by status and determine their types
for (const file of changedFilesList) {
if (!file.filePath) {
logger.warn("Skipping file change entry with missing filePath");
continue;
}
const { status } = file;
if (status === "renamed" && !file.oldFilePath) {
logger.warn(
`Renamed file ${file.filePath} is missing oldFilePath, treating as added`
);
grouped.added.push({
...file,
fileType: this.determineFileType(file.filePath),
});
continue;
}
if (grouped[status]) {
grouped[status].push({
...file,
fileType: this.determineFileType(file.filePath),
});
} else {
logger.warn(
`Unknown file status: ${status} for file ${file.filePath}`
);
}
}
// Log summary of files to process
logger.info(
`Files to process: ${grouped.added.length} added, ${grouped.modified.length} modified, ` +
`${grouped.deleted.length} deleted, ${grouped.renamed.length} renamed`
);
// Process each file according to its status and type
const processingResults = {
added: { processed: 0, skipped: 0 },
modified: { processed: 0, skipped: 0 },
deleted: { processed: 0, skipped: 0 },
renamed: { processed: 0, skipped: 0 },
};
// Process deleted files
if (grouped.deleted.length > 0) {
logger.info(`Processing ${grouped.deleted.length} deleted files`);
await this.processDeletedFiles(
grouped.deleted,
processingResults.deleted
);
}
// Process renamed files
if (grouped.renamed.length > 0) {
logger.info(`Processing ${grouped.renamed.length} renamed files`);
await this.processRenamedFiles(
grouped.renamed,
processingResults.renamed
);
}
// Process added files
if (grouped.added.length > 0) {
logger.info(`Processing ${grouped.added.length} added files`);
await this.processAddedOrModifiedFiles(
grouped.added,
"added",
processingResults.added
);
}
// Process modified files
if (grouped.modified.length > 0) {
logger.info(`Processing ${grouped.modified.length} modified files`);
await this.processAddedOrModifiedFiles(
grouped.modified,
"modified",
processingResults.modified
);
}
logger.info(
`Completed processing ${changedFilesList.length} file changes`
);
return {
processed: changedFilesList.length,
summary: {
added: grouped.added.length,
modified: grouped.modified.length,
deleted: grouped.deleted.length,
renamed: grouped.renamed.length,
},
results: processingResults,
};
} catch (error) {
logger.error(`Error processing file changes: ${error.message}`, {
error,
fileCount: changedFilesList?.length || 0,
});
throw error;
}
}
/**
* Process renamed files - treat as a delete of oldFilePath and an add of filePath
* @param {Array<Object>} renamedFiles - List of renamed files with their types
* @param {Object} results - Object to record processing results
* @returns {Promise<void>}
*/
async processRenamedFiles(renamedFiles, results) {
for (const file of renamedFiles) {
const { filePath, oldFilePath, fileType } = file;
try {
// Skip non-code and non-markdown files (currently only processing code files)
if (fileType.type !== "code" && fileType.type !== "markdown") {
logger.debug(
`Skipping renamed non-processable file: ${oldFilePath} -> ${filePath} (${fileType.type})`
);
results.skipped++;
continue;
}
if (fileType.type === "markdown") {
logger.info(
`Processing renamed Markdown file: ${oldFilePath} -> ${filePath}`
);
// Step 1: Process the oldFilePath as 'deleted' - adapted from processDeletedFiles logic
logger.info(`Processing old path ${oldFilePath} as deleted`);
let documentId = null;
try {
// Get the document ID for the old Markdown file path
const document = await this.dbQueries.getProjectDocumentByFilePath(
this.dbClient,
oldFilePath
);
if (document) {
documentId = document.document_id;
logger.info(
`Found document ID ${documentId} for old Markdown file path: ${oldFilePath}`
);
// Cancel any background AI jobs for this document
try {
const cancelResult =
await this.dbQueries.cancelBackgroundAiJobsForEntity(
this.dbClient,
documentId
);
logger.info(
`Cancelled ${cancelResult.deletedCount} background AI jobs for document ID: ${documentId}`
);
} catch (jobError) {
logger.error(
`Error cancelling jobs for document ${documentId}: ${jobError.message}`,
{
error: jobError,
documentId,
filePath: oldFilePath,
}
);
// Continue with document deletion despite job cancellation errors
}
// Delete the project document entry for the old path
try {
const deleteResult =
await this.dbQueries.deleteProjectDocumentByFilePath(
this.dbClient,
oldFilePath
);
logger.info(
`Deleted ${deleteResult.deletedCount} project document for old file path: ${oldFilePath}`
);
} catch (deleteError) {
logger.error(
`Error deleting project document for old file path ${oldFilePath}: ${deleteError.message}`,
{
error: deleteError,
documentId,
filePath: oldFilePath,
}
);
// This is an error, but we'll continue with processing
}
} else {
logger.info(
`No document found for old Markdown file path: ${oldFilePath}`
);
}
} catch (documentError) {
logger.error(
`Error fetching project document for old file path ${oldFilePath}: ${documentError.message}`,
{
error: documentError,
filePath: oldFilePath,
}
);
}
// Step 2: Process the new filePath as 'added'
// Note: Full implementation will be added in Task 064
logger.info(
`New file path ${filePath} will be processed as 'added' in Task 064`
);
logger.info(
`Completed processing renamed Markdown file: ${oldFilePath} -> ${filePath}`
);
results.processed++;
continue;
}
logger.info(
`Processing renamed code file: ${oldFilePath} -> ${filePath} (${fileType.language})`
);
// Step 1: Process oldFilePath as 'deleted'
// This is essentially the same logic as in processDeletedFiles
// First fetch all entity IDs for the old file path before deleting anything
let entityIds = [];
try {
const entities = await this.dbQueries.getCodeEntitiesByFilePath(
this.dbClient,
oldFilePath
);
entityIds = entities.map((entity) => entity.entity_id);
logger.info(
`Found ${entityIds.length} entities to remove for old file path: ${oldFilePath}`
);
} catch (error) {
logger.error(
`Error fetching entities for old file path ${oldFilePath}: ${error.message}`,
{ error }
);
// Continue with deletion anyway - the old file is gone, so entities should be removed
}
// Cancel background AI jobs for each entity ID from the old file path
let cancelledJobsCount = 0;
if (entityIds.length > 0) {
logger.info(
`Cancelling background jobs for ${entityIds.length} entities in old file path: ${oldFilePath}`
);
for (const entityId of entityIds) {
try {
const result =
await this.dbQueries.cancelBackgroundAiJobsForEntity(
this.dbClient,
entityId
);
cancelledJobsCount += result.deletedCount || 0;
} catch (error) {
logger.error(
`Error cancelling jobs for entity ${entityId}: ${error.message}`,
{
error,
entityId,
filePath: oldFilePath,
}
);
// Continue with other entities
}
}
logger.info(
`Cancelled ${cancelledJobsCount} background jobs for old file path: ${oldFilePath}`
);
}
// Delete code relationships for entities in the old file path
try {
const relationshipsResult =
await this.dbQueries.deleteCodeRelationshipsByFilePath(
this.dbClient,
oldFilePath
);
logger.info(
`Deleted ${relationshipsResult.deletedCount} code relationships for old file path: ${oldFilePath}`
);
} catch (error) {
logger.error(
`Error deleting code relationships for old file path ${oldFilePath}: ${error.message}`,
{
error,
filePath: oldFilePath,
}
);
// Continue with entity deletion - relationships are less critical
}
// Delete code entities for the old file path
try {
const entitiesResult =
await this.dbQueries.deleteCodeEntitiesByFilePath(
this.dbClient,
oldFilePath
);
logger.info(
`Deleted ${entitiesResult.deletedCount} code entities for old file path: ${oldFilePath}`
);
} catch (error) {
logger.error(
`Error deleting code entities for old file path ${oldFilePath}: ${error.message}`,
{
error,
filePath: oldFilePath,
}
);
// This is a critical error, but we'll continue with processing the new file path
}
// Step 2: Process filePath (new path) as 'added'
// In the initial implementation, we just log this as we would in processFileChanges
// This part will be expanded when the 'added' file handling is implemented (Task 053)
logger.debug(
`New file path ${filePath} will be processed as 'added' in a subsequent task`
);
logger.info(
`Completed processing renamed file: ${oldFilePath} -> ${filePath}`
);
results.processed++;
} catch (error) {
logger.error(
`Error processing renamed file ${oldFilePath} -> ${filePath}: ${error.message}`,
{
error,
oldFilePath,
filePath,
fileType,
}
);
results.skipped++;
}
}
}
/**
* Process deleted files - remove code entities, relationships, and cancel jobs
* @param {Array<Object>} deletedFiles - List of deleted files with their types
* @param {Object} results - Object to record processing results
* @returns {Promise<void>}
*/
async processDeletedFiles(deletedFiles, results) {
for (const file of deletedFiles) {
const { filePath, fileType } = file;
try {
// Check for Markdown files specifically
if (fileType.type === "markdown") {
logger.info(`Processing deleted Markdown file: ${filePath}`);
// Step 1: Get the document ID for the Markdown file
let documentId = null;
try {
const document = await this.dbQueries.getProjectDocumentByFilePath(
this.dbClient,
filePath
);
if (document) {
documentId = document.document_id;
logger.info(
`Found document ID ${documentId} for Markdown file: ${filePath}`
);
// Step 2: Cancel any background AI jobs for this document
try {
const cancelResult =
await this.dbQueries.cancelBackgroundAiJobsForEntity(
this.dbClient,
documentId
);
logger.info(
`Cancelled ${cancelResult.deletedCount} background AI jobs for document ID: ${documentId}`
);
} catch (jobError) {
logger.error(
`Error cancelling jobs for document ${documentId}: ${jobError.message}`,
{
error: jobError,
documentId,
filePath,
}
);
// Continue with document deletion despite job cancellation errors
}
// Step 3: Delete the project document entry
try {
const deleteResult =
await this.dbQueries.deleteProjectDocumentByFilePath(
this.dbClient,
filePath
);
logger.info(
`Deleted ${deleteResult.deletedCount} project document for file: ${filePath}`
);
} catch (deleteError) {
logger.error(
`Error deleting project document for file ${filePath}: ${deleteError.message}`,
{
error: deleteError,
documentId,
filePath,
}
);
// This is a critical error, but we'll continue with other files
}
} else {
logger.info(
`No document found for deleted Markdown file: ${filePath}`
);
}
} catch (documentError) {
logger.error(
`Error fetching project document for file ${filePath}: ${documentError.message}`,
{
error: documentError,
filePath,
}
);
// Continue with other files
}
logger.info(
`Completed processing deleted Markdown file: ${filePath}`
);
results.processed++;
continue;
}
// Only process code files (files that could have code entities)
if (fileType.type !== "code") {
logger.debug(
`Skipping deleted non-code file: ${filePath} (${fileType.type})`
);
results.skipped++;
continue;
}
logger.info(
`Processing deleted code file: ${filePath} (${fileType.language})`
);
// Step 1: First fetch all entity IDs for this file path before deleting anything
// This allows us to properly cancel jobs for these entities
let entityIds = [];
try {
const entities = await this.dbQueries.getCodeEntitiesByFilePath(
this.dbClient,
filePath
);
entityIds = entities.map((entity) => entity.entity_id);
logger.info(
`Found ${entityIds.length} entities to remove for file: ${filePath}`
);
} catch (error) {
logger.error(
`Error fetching entities for file ${filePath}: ${error.message}`,
{ error }
);
// Continue with deletion anyway - the file is gone, so entities should be removed
}
// Step 2: Cancel background AI jobs for each entity ID
let cancelledJobsCount = 0;
if (entityIds.length > 0) {
logger.info(
`Cancelling background jobs for ${entityIds.length} entities in file: ${filePath}`
);
for (const entityId of entityIds) {
try {
const result =
await this.dbQueries.cancelBackgroundAiJobsForEntity(
this.dbClient,
entityId
);
cancelledJobsCount += result.deletedCount || 0;
} catch (error) {
logger.error(
`Error cancelling jobs for entity ${entityId}: ${error.message}`,
{
error,
entityId,
filePath,
}
);
// Continue with other entities
}
}
logger.info(
`Cancelled ${cancelledJobsCount} background jobs for file: ${filePath}`
);
}
// Step 3: Delete code relationships for entities in this file path
try {
const relationshipsResult =
await this.dbQueries.deleteCodeRelationshipsByFilePath(
this.dbClient,
filePath
);
logger.info(
`Deleted ${relationshipsResult.deletedCount} code relationships for file: ${filePath}`
);
} catch (error) {
logger.error(
`Error deleting code relationships for file ${filePath}: ${error.message}`,
{
error,
filePath,
}
);
// Continue with entity deletion - relationships are less critical
}
// Step 4: Delete code entities for this file path
try {
const entitiesResult =
await this.dbQueries.deleteCodeEntitiesByFilePath(
this.dbClient,
filePath
);
logger.info(
`Deleted ${entitiesResult.deletedCount} code entities for file: ${filePath}`
);
} catch (error) {
logger.error(
`Error deleting code entities for file ${filePath}: ${error.message}`,
{
error,
filePath,
}
);
// This is a critical error, but we'll continue with other files
}
logger.info(`Completed processing deleted file: ${filePath}`);
results.processed++;
} catch (error) {
logger.error(
`Error processing deleted file ${filePath}: ${error.message}`,
{
error,
filePath,
fileType,
}
);
results.skipped++;
}
}
}
/**
* Process added or modified files - read file content and check size
* @param {Array<Object>} files - List of files with their types
* @param {string} status - Status of the files ('added' or 'modified')
* @param {Object} results - Object to record processing results
* @returns {Promise<void>}
*/
async processAddedOrModifiedFiles(files, status, results) {
// Get the maximum file size from config, convert from MB to bytes
const MAX_TEXT_FILE_SIZE_BYTES =
(config.MAX_TEXT_FILE_SIZE_MB || 5) * 1024 * 1024;
for (const file of files) {
const { filePath, fileType } = file;
try {
logger.info(
`Processing ${status} ${fileType.type} file: ${filePath}${
fileType.language ? ` (${fileType.language})` : ""
}`
);
// Skip ignored files
if (fileType.type === "ignored") {
logger.debug(`Skipping ignored file: ${filePath}`);
results.skipped++;
continue;
}
try {
// Read the file content
const fileContent = await fs.readFile(filePath, "utf-8");
// Get the size of the content in bytes
const fileSize = Buffer.byteLength(fileContent, "utf-8");
// Check if the file exceeds the maximum size
if (fileSize > MAX_TEXT_FILE_SIZE_BYTES) {
logger.warn(
`File ${filePath} exceeds maximum size (${fileSize} bytes > ${MAX_TEXT_FILE_SIZE_BYTES} bytes), skipping full parsing`
);
// Store a minimal code entity for files that are too large
if (fileType.type === "code") {
try {
const fileName = path.basename(filePath);
const entityId = uuidv4();
const entityData = {
entity_id: entityId,
file_path: filePath,
entity_type: "file", // A generic file type
name: fileName,
start_line: 1,
start_column: 1,
end_line: 1,
end_column: 1,
raw_content: null, // Don't store the content as it's too large
language: fileType.language,
content_hash: null,
parent_entity_id: null,
parsing_status: "skipped_too_large",
ai_status: "skipped",
custom_metadata: JSON.stringify({
fileSize: fileSize,
maxAllowedSize: MAX_TEXT_FILE_SIZE_BYTES,
reason: "File exceeds size limit",
}),
};
logger.debug(
`Storing minimal code entity for oversized file: ${filePath}`
);
await this.dbQueries.addOrUpdateCodeEntity(
this.dbClient,
entityData
);
logger.info(
`Stored minimal code entity record for oversized file: ${filePath}`
);
} catch (dbError) {
logger.error(
`Error storing minimal entity for oversized file ${filePath}: ${dbError.message}`,
{
error: dbError,
filePath,
fileType,
}
);
}
}
// For Markdown files, similar handling (will be implemented fully in later tasks)
else if (fileType.type === "markdown") {
logger.debug(
`Identified oversized Markdown file: ${filePath} - will be handled in future implementation`
);
try {
const fileName = path.basename(filePath);
// Get existing document ID if it exists, or generate a new one
let document =
await this.dbQueries.getProjectDocumentByFilePath(
this.dbClient,
filePath
);
let documentId = document?.document_id || uuidv4();
// Create minimal document record for the oversized file
const docData = {
document_id: documentId,
file_path: filePath,
file_type: "markdown",
raw_content: null, // Don't store content as it's too large
content_hash: null,
parsing_status: "skipped_too_large",
ai_status: "skipped",
custom_metadata: JSON.stringify({
fileSize: fileSize,
maxAllowedSize: MAX_TEXT_FILE_SIZE_BYTES,
reason: "File exceeds size limit",
}),
};
logger.debug(
`Storing minimal document record for oversized Markdown file: ${filePath}`
);
await this.dbQueries.addOrUpdateProjectDocument(
this.dbClient,
docData
);
logger.info(
`Stored minimal document record for oversized Markdown file: ${filePath}`
);
} catch (dbError) {
logger.error(
`Error storing minimal document for oversized Markdown file ${filePath}: ${dbError.message}`,
{
error: dbError,
filePath,
fileType,
}
);
}
}
// For other document files, similar handling
else if (fileType.type === "text") {
logger.debug(
`Will store minimal document record for oversized file: ${filePath}`
);
// This will be implemented in a later task
}
results.processed++;
continue; // Skip further processing for this file
}
logger.info(
`File ${filePath} (${fileSize} bytes) is within size limit, proceeding to parsing`
);
// If we've reached here, the file content has been read and is within size limits
// Process Markdown files
if (fileType.type === "markdown") {
try {
logger.info(`Processing ${status} Markdown file: ${filePath}`);
// Parse the Markdown content
const parseResult = await this.parserService.parseMarkdownFile(
filePath,
fileContent
);
// Handle parsing errors
if (parseResult.errors && parseResult.errors.length > 0) {
logger.error(
`Error parsing Markdown file ${filePath}: ${parseResult.errors[0]}`
);
// Get existing document ID if it exists, or generate a new one
let document =
await this.dbQueries.getProjectDocumentByFilePath(
this.dbClient,
filePath
);
let documentId = document?.document_id || uuidv4();
// Store a document record with failed status
const docData = {
document_id: documentId,
file_path: filePath,
file_type: "markdown",
raw_content: fileContent, // Still store the content for potential manual review
content_hash: null,
parsing_status: "failed_read",
ai_status: "skipped",
custom_metadata: JSON.stringify({
errors: parseResult.errors,
reason: "Failed to parse markdown",
}),
};
await this.dbQueries.addOrUpdateProjectDocument(
this.dbClient,
docData
);
logger.info(
`Stored document record with parsing errors for Markdown file: ${filePath}`
);
results.processed++;
continue;
}
// If parsing was successful and raw content is available
if (parseResult.rawContent) {
// Get existing document ID if it exists, or generate a new one
let document =
await this.dbQueries.getProjectDocumentByFilePath(
this.dbClient,
filePath
);
let documentId = document?.document_id || uuidv4();
// Calculate content hash
const contentHash = crypto
.createHash("sha256")
.update(parseResult.rawContent)
.digest("hex");
// Check if content has changed if it's an existing document
const contentChanged =
!document || document.content_hash !== contentHash;
// Prepare document data
const docData = {
document_id: documentId,
file_path: filePath,
file_type: "markdown",
raw_content: parseResult.rawContent,
content_hash: contentHash,
parsing_status: "completed",
ai_status: "pending", // Will be processed by AI job
};
// Store or update document record
await this.dbQueries.addOrUpdateProjectDocument(
this.dbClient,
docData
);
logger.info(
`Successfully stored/updated document record for Markdown file: ${filePath}`
);
// If document is new or content has changed, enqueue an AI job for processing
if (contentChanged) {
logger.info(
`Content changed for ${filePath}, enqueueing AI job`
);
try {
await this.jobManager.enqueueJob({
task_type: "enrich_entity_summary_keywords",
target_entity_id: documentId,
target_entity_type: "project_document",
payload: {},
});
logger.info(
`Successfully enqueued AI job for document: ${documentId}`
);
} catch (jobError) {
logger.error(
`Error enqueueing AI job for document ${documentId}: ${jobError.message}`,
{
error: jobError,
documentId,
filePath,
}
);
}
} else {
logger.info(
`Content unchanged for ${filePath}, skipping AI job`
);
}
} else {
logger.warn(
`No raw content available for Markdown file: ${filePath}`
);
}
results.processed++;
continue;
} catch (parseError) {
logger.error(
`Error during processing of Markdown file ${filePath}: ${parseError.message}`,
{
error: parseError,
filePath,
}
);
results.errors++;
continue;
}
}
// For code files, process with the parser
if (fileType.type === "code" && fileType.language) {
// Check if language is supported by Tree-sitter
const supportedLanguages = config.TREE_SITTER_LANGUAGES || [
"javascript",
"typescript",
"python",
];
if (supportedLanguages.includes(fileType.language)) {
try {
logger.info(
`Parsing code file ${filePath} with language: ${fileType.language}`
);
// Call the parser service
const parseResult = await this.parserService.parseCodeFile(
filePath,
fileContent,
fileType.language
);
// Check for parsing errors
if (parseResult.errors && parseResult.errors.length > 0) {
logger.warn(
`Parser reported ${parseResult.errors.length} errors for file ${filePath}`,
{ errors: parseResult.errors }
);
// Store a minimal code entity with parsing_status: 'failed_parsing'
try {
const fileName = path.basename(filePath);
const entityId = uuidv4();
const entityData = {
entity_id: entityId,
file_path: filePath,
entity_type: "file", // A generic file type
name: fileName,
start_line: 1,
start_column: 1,
end_line: 1,
end_column: 1,
raw_content: null,
language: fileType.language,
content_hash: null,
parent_entity_id: null,
parsing_status: "failed_parsing",
ai_status: "skipped",
custom_metadata: {
parsingErrors: parseResult.errors,
reason: "Parser reported errors",
},
};
logger.debug(
`Storing code entity with failed_parsing status for file: ${filePath}`
);
await this.dbQueries.addOrUpdateCodeEntity(
this.dbClient,
entityData
);
logger.info(
`Stored code entity record with failed_parsing status for file: ${filePath}`
);
} catch (dbError) {
logger.error(
`Error storing entity with failed_parsing status for file ${filePath}: ${dbError.message}`,
{
error: dbError,
filePath,
fileType,
}
);
}
} else {
// Successful parsing
logger.info(
`Successfully parsed ${filePath}: found ${
parseResult.entities?.length || 0
} entities and ${
parseResult.relationships?.length || 0
} relationships`
);
// Process and store the entities
const entityMap = await this.processCodeEntities(
parseResult.entities,
filePath,
fileType.language
);
// Process and store relationships
if (
parseResult.relationships &&
parseResult.relationships.length > 0
) {
await this.processCodeRelationships(
parseResult.relationships,
filePath,
entityMap
);
} else {
logger.debug(
`No relationships to process for file: ${filePath}`
);
}
}
} catch (parseError) {
// Handle parser exceptions
logger.error(
`Error parsing file ${filePath}: ${parseError.message}`,
{
error: parseError,
filePath,
language: fileType.language,
}
);
// Store a minimal code entity with parsing_status: 'failed_parsing'
try {
const fileName = path.basename(filePath);
const entityId = uuidv4();
const entityData = {
entity_id: entityId,
file_path: filePath,
entity_type: "file", // A generic file type
name: fileName,
start_line: 1,
start_column: 1,
end_line: 1,
end_column: 1,
raw_content: null,
language: fileType.language,
content_hash: null,
parent_entity_id: null,
parsing_status: "failed_parsing",
ai_status: "skipped",
custom_metadata: {
error: parseError.message,
reason: "Parser exception",
},
};
logger.debug(
`Storing code entity with failed_parsing status for file: ${filePath}`
);
await this.dbQueries.addOrUpdateCodeEntity(
this.dbClient,
entityData
);
logger.info(
`Stored code entity record with failed_parsing status for file: ${filePath}`
);
} catch (dbError) {
logger.error(
`Error storing entity with failed_parsing status for file ${filePath}: ${dbError.message}`,
{
error: dbError,
filePath,
fileType,
}
);
}
}
} else {
// Language not supported by Tree-sitter
logger.info(
`Language ${fileType.language} not supported for Tree-sitter parsing, skipping parser for file: ${filePath}`
);
// Store as a regular file entity without detailed code structure
// This will be implemented in a later task
logger.debug(
`Will store as basic file entity without Tree-sitter parsing: ${filePath}`
);
}
} else if (fileType.type === "text") {
// Text files don't need Tree-sitter parsing
logger.debug(
`Text file ${filePath} will be processed in a subsequent task`
);
}
results.processed++;
} catch (readError) {
// Handle file read errors
logger.error(`Error reading file ${filePath}: ${readError.message}`, {
error: readError,
filePath,
});
results.skipped++;
continue; // Skip further processing for this file
}
} catch (error) {
logger.error(
`Error processing ${status} file ${filePath}: ${error.message}`,
{
error,
filePath,
fileType,
status,
}
);
results.skipped++;
}
}
}
/**
* Process code entities extracted from a file
* @param {Array<Object>} entities - List of code entities extracted by the parser
* @param {string} filePath - Path to the file the entities were extracted from
* @param {string} language - Programming language of the file
* @returns {Promise<Object>} Map of original entity references to their generated UUIDs
*/
async processCodeEntities(entities, filePath, language) {
if (!entities || entities.length === 0) {
logger.debug(`No entities to process for file: ${filePath}`);
return {};
}
logger.info(
`Processing ${entities.length} code entities for file: ${filePath}`
);
// Track successful and failed entity operations
const results = {
added: 0,
updated: 0,
failed: 0,
jobsEnqueued: 0,
};
// Create a map to store the relationship between original entity references and their UUIDs
// This will be used to resolve relationships properly
const entityMap = {};
for (const entity of entities) {
try {
// Generate a unique ID for the entity
const entityId = uuidv4();
entity.entity_id = entityId;
// Store any original reference ID or name that might be used in relationships
if (entity.ref_id) {
entityMap[entity.ref_id] = entityId;
}
// Also map by entity name and type as a fallback
const nameTypeKey = `${entity.entity_type}:${entity.name}`;
entityMap[nameTypeKey] = entityId;
// Calculate content hash
const contentHash = crypto
.createHash("sha256")
.update(entity.raw_content || "")
.digest("hex");
entity.content_hash = contentHash;
// Prepare the full entity data for DB insertion/update
const entityData = {
entity_id: entityId,
file_path: filePath,
entity_type: entity.entity_type,
name: entity.name,
start_line: entity.start_line,
start_column: entity.start_column,
end_line: entity.end_line,
end_column: entity.end_column,
raw_content: entity.raw_content,
language,
content_hash: contentHash,
parent_entity_id: entity.parent_entity_id, // If provided by parser
parsing_status: "completed",
ai_status: "pending",
custom_metadata: entity.custom_metadata || {},
};
// Add or update the entity in the database
try {
const result = await this.dbQueries.addOrUpdateCodeEntity(
this.dbClient,
entityData
);
if (result.isNew || result.contentChanged) {
// Entity is new or has changed, enqueue an AI job to process it
logger.debug(
`Enqueueing AI job for ${
result.isNew ? "new" : "updated"
} entity: ${entityId}`
);
try {
await this.jobManager.enqueueJob({
task_type: "enrich_entity_summary_keywords",
target_entity_id: entityId,
target_entity_type: "code_entity",
payload: {},
});
results.jobsEnqueued++;
} catch (jobError) {
logger.error(
`Error enqueueing AI job for entity ${entityId}: ${jobError.message}`,
{
error: jobError,
entityId,
filePath,
}
);
}
if (result.isNew) {
results.added++;
} else {
results.updated++;
}
} else {
logger.debug(
`Entity ${entityId} already exists and content hasn't changed, skipping AI job`
);
results.updated++;
}
} catch (dbError) {
logger.error(
`Error storing entity for ${filePath}: ${dbError.message}`,
{
error: dbError,
entityId,
filePath,
entityType: entity.entity_type,
}
);
results.failed++;
}
} catch (error) {
logger.error(
`Error processing entity in file ${filePath}: ${error.message}`,
{
error,
filePath,
entityType: entity.entity_type,
}
);
results.failed++;
}
}
logger.info(
`Completed processing entities for ${filePath}: ${results.added} added, ${results.updated} updated, ` +
`${results.failed} failed, ${results.jobsEnqueued} AI jobs enqueued`
);
return entityMap;
}
/**
* Process code relationships extracted from a file
* @param {Array<Object>} relationships - List of code relationships extracted by the parser
* @param {string} filePath - Path to the file the relationships were extracted from
* @param {Object} entityMap - Map of entity original references to their UUIDs
* @returns {Promise<void>}
*/
async processCodeRelationships(relationships, filePath, entityMap) {
if (!relationships || relationships.length === 0) {
logger.debug(`No relationships to process for file: ${filePath}`);
return;
}
logger.info(
`Processing ${relationships.length} code relationships for file: ${filePath}`
);
// Track successful and failed relationship operations
const results = {
added: 0,
failed: 0,
};
// First, clean up existing relationships for this file to handle modifications
try {
logger.debug(`Cleaning up existing relationships for file: ${filePath}`);
const deleteResult =
await this.dbQueries.deleteCodeRelationshipsByFilePath(
this.dbClient,
filePath
);
logger.info(
`Deleted ${
deleteResult.deletedCount || 0
} existing relationships for file: ${filePath}`
);
} catch (deleteError) {
logger.error(
`Error deleting existing relationships for file ${filePath}: ${deleteError.message}`,
{ error: deleteError, filePath }
);
// Continue with adding new relationships even if cleanup failed
}
// Process each relationship
for (const relationship of relationships) {
try {
// Generate a unique ID for the relationship
const relationshipId = uuidv4();
// Resolve source entity ID using the entityMap
let sourceEntityId = null;
if (
relationship.source_ref_id &&
entityMap[relationship.source_ref_id]
) {
sourceEntityId = entityMap[relationship.source_ref_id];
} else if (
relationship.source_entity_type &&
relationship.source_entity_name
) {
const sourceKey = `${relationship.source_entity_type}:${relationship.source_entity_name}`;
sourceEntityId = entityMap[sourceKey];
}
if (!sourceEntityId) {
logger.warn(
`Could not resolve source entity ID for relationship in file ${filePath}`,
{ relationship }
);
results.failed++;
continue;
}
// Resolve target entity ID if it's in the same file
let targetEntityId = null;
if (
relationship.target_ref_id &&
entityMap[relationship.target_ref_id]
) {
targetEntityId = entityMap[relationship.target_ref_id];
} else if (
relationship.target_entity_type &&
relationship.target_entity_name
) {
const targetKey = `${relationship.target_entity_type}:${relationship.target_entity_name}`;
targetEntityId = entityMap[targetKey];
}
// If target entity is not found in the map, it might be in another file
// We'll store the relationship with target_entity_id as null and rely on target_symbol_name
// Prepare relationship data for DB insertion
const relationshipData = {
relationship_id: relationshipId,
source_entity_id: sourceEntityId,
target_entity_id: targetEntityId, // May be null for cross-file relationships
target_symbol_name: relationship.target_symbol_name,
relationship_type: relationship.relationship_type,
custom_metadata: relationship.custom_metadata || {},
};
// Add the relationship to the database
try {
await this.dbQueries.addCodeRelationship(
this.dbClient,
relationshipData
);
results.added++;
} catch (dbError) {
logger.error(
`Error storing relationship for ${filePath}: ${dbError.message}`,
{
error: dbError,
relationshipId,
sourceEntityId,
targetEntityId,
filePath,
}
);
results.failed++;
}
} catch (error) {
logger.error(
`Error processing relationship in file ${filePath}: ${error.message}`,
{
error,
filePath,
relationshipType: relationship.relationship_type,
}
);
results.failed++;
}
}
logger.info(
`Completed processing relationships for ${filePath}: ${results.added} added, ${results.failed} failed`
);
}
}
// Export a singleton instance and the class
export default new IndexingService({ dbClient: null });
|