@c4a/extract-thrift 0.7.5 → 0.7.9

package/index.js

@@ -11444,15 +11444,21 @@ function replaceWithCount(value, pattern, replacement, count) {
     return replacement(...args.slice(0, -2));
   });
 }
+var SECRET_TEXT_KEY = "(?:[A-Za-z0-9_.-]*(?:password|passwd|pwd|secret|token|credential|cookie)[A-Za-z0-9_.-]*|api[-_]?key|access[-_]?(?:key|token)|private[-_]?key|client[-_]?secret|authorization)";
+var SECRET_TEXT_ASSIGNMENT = `(?:=\\s*|:\\s+(?=\\S)|:\\s*(?=["']))`;
+var AUTHORIZATION_TEXT_PATTERN = new RegExp(`(\\bauthorization\\s*:\\s*(?:bearer|basic)\\s+)` + `(?!${escapeRegExp(INDEXER_OUTPUT_REDACTION_MARKER)})[^\\s,;]+`, "giu");
+var QUERY_SECRET_TEXT_PATTERN = new RegExp(`([?&](?:access_token|refresh_token|api_key|password|secret)=)` + `(?!${escapeRegExp(INDEXER_OUTPUT_REDACTION_MARKER)})[^&#\\s]+`, "giu");
+var ASSIGNMENT_SECRET_TEXT_PATTERN = new RegExp(`((?:["']?${SECRET_TEXT_KEY}["']?)\\s*${SECRET_TEXT_ASSIGNMENT})` + `(?!["']?${escapeRegExp(INDEXER_OUTPUT_REDACTION_MARKER)})` + `(?:"(?:\\\\.|[^"])*"|'(?:\\\\.|[^'])*'|[^\\s,;}\\]]+)`, "giu");
 function redactKnownText(value, count) {
+  if (!value.includes(":") && !value.includes("=") && !value.includes("-----BEGIN ")) {
+    return value;
+  }
   let output = value;
   output = replaceWithCount(output, /-----BEGIN (?:RSA |EC |OPENSSH )?PRIVATE KEY-----[\s\S]*?-----END (?:RSA |EC |OPENSSH )?PRIVATE KEY-----/gu, INDEXER_OUTPUT_REDACTION_MARKER, count);
-  output = replaceWithCount(output, new RegExp(`(\\bauthorization\\s*:\\s*(?:bearer|basic)\\s+)` + `(?!${escapeRegExp(INDEXER_OUTPUT_REDACTION_MARKER)})[^\\s,;]+`, "giu"), (_match, prefix) => `${prefix}${INDEXER_OUTPUT_REDACTION_MARKER}`, count);
+  output = replaceWithCount(output, AUTHORIZATION_TEXT_PATTERN, (_match, prefix) => `${prefix}${INDEXER_OUTPUT_REDACTION_MARKER}`, count);
   output = replaceWithCount(output, /([a-z][a-z0-9+.-]*:\/\/)[^\s/@:]+:[^\s/@]+@/giu, (_match, prefix) => `${prefix}${INDEXER_OUTPUT_REDACTION_MARKER}@`, count);
-  output = replaceWithCount(output, new RegExp(`([?&](?:access_token|refresh_token|api_key|password|secret)=)` + `(?!${escapeRegExp(INDEXER_OUTPUT_REDACTION_MARKER)})[^&#\\s]+`, "giu"), (_match, prefix) => `${prefix}${INDEXER_OUTPUT_REDACTION_MARKER}`, count);
-  const key = "(?:[A-Za-z0-9_.-]*(?:password|passwd|pwd|secret|token|credential|cookie)[A-Za-z0-9_.-]*|api[-_]?key|access[-_]?(?:key|token)|private[-_]?key|client[-_]?secret|authorization)";
-  const assignment = `(?:=\\s*|:\\s+(?=\\S)|:\\s*(?=["']))`;
-  output = replaceWithCount(output, new RegExp(`((?:["']?${key}["']?)\\s*${assignment})` + `(?!["']?${escapeRegExp(INDEXER_OUTPUT_REDACTION_MARKER)})` + `(?:"(?:\\\\.|[^"])*"|'(?:\\\\.|[^'])*'|[^\\s,;}\\]]+)`, "giu"), (_match, prefix) => `${prefix}"${INDEXER_OUTPUT_REDACTION_MARKER}"`, count);
+  output = replaceWithCount(output, QUERY_SECRET_TEXT_PATTERN, (_match, prefix) => `${prefix}${INDEXER_OUTPUT_REDACTION_MARKER}`, count);
+  output = replaceWithCount(output, ASSIGNMENT_SECRET_TEXT_PATTERN, (_match, prefix) => `${prefix}"${INDEXER_OUTPUT_REDACTION_MARKER}"`, count);
   return output;
 }
 function redactBlockedText(value, blocked, count) {
@@ -12018,6 +12024,59 @@ var INDEXABLE_EXTENSIONS = new Set([
 var UPLOAD_ALLOWED_EXTENSIONS = collectExtensions(() => true);
 var TEXT_EXTENSIONS = collectExtensions((definition) => definition.cas.encoding === "utf8");
 var UPLOAD_MAX_FILE_SIZE = 5 * 1024 * 1024;
+// src/thriftFields.ts
+function thriftFields(tokens) {
+  const fields = [];
+  for (let index = 0;index < tokens.length; index++) {
+    if (tokens[index]?.kind !== "number" || tokens[index + 1]?.value !== ":")
+      continue;
+    const number = tokens[index].value;
+    let cursor = index + 2;
+    const label = tokens[cursor]?.value;
+    if (label === "optional" || label === "required")
+      cursor++;
+    const typeStart = cursor++;
+    if (tokens[cursor]?.value === "<") {
+      let depth = 0;
+      do {
+        if (tokens[cursor]?.value === "<")
+          depth++;
+        if (tokens[cursor]?.value === ">")
+          depth--;
+        cursor++;
+      } while (cursor < tokens.length && depth > 0);
+    }
+    const name = tokens[cursor];
+    if (name?.kind !== "identifier")
+      continue;
+    const type = tokens.slice(typeStart, cursor).map((token) => token.value).join("");
+    cursor++;
+    let defaultValue;
+    if (tokens[cursor]?.value === "=") {
+      const start = ++cursor;
+      let depth = 0;
+      do {
+        if (["[", "{"].includes(tokens[cursor]?.value ?? ""))
+          depth++;
+        if (["]", "}"].includes(tokens[cursor]?.value ?? ""))
+          depth--;
+        cursor++;
+      } while (cursor < tokens.length && depth > 0);
+      defaultValue = tokens.slice(start, cursor).map((token) => token.kind === "string" ? JSON.stringify(token.value) : token.value).join("");
+    }
+    fields.push({
+      name: name.value,
+      type,
+      number,
+      ...label === "optional" ? { optional: true } : label === "required" ? { optional: false } : {},
+      ...defaultValue === undefined ? {} : { defaultValue },
+      location: { line: name.line, column: name.column }
+    });
+    index = cursor - 1;
+  }
+  return fields;
+}
+
 // src/thriftParser.ts
 import { posix } from "node:path";
 
@@ -12206,11 +12265,14 @@ function parseMethods(path2, serviceName, tokens) {
       name: nameToken.value,
       return_type: tokenText(returnTokens),
       oneway,
+      fields: thriftFields(tokens.slice(open + 1, matching(tokens, open, "(", ")"))),
       locator: { path: path2, line: nameToken.line, column: nameToken.column }
     });
     index = matching(tokens, open, "(", ")") + 1;
     if (tokens[index]?.value === "throws" && tokens[index + 1]?.value === "(") {
-      index = matching(tokens, index + 1, "(", ")") + 1;
+      const end = matching(tokens, index + 1, "(", ")");
+      methods.at(-1).throws = thriftFields(tokens.slice(index + 2, end));
+      index = end + 1;
     }
     if (tokens[index]?.value === "(") {
       const parsed = parseAnnotationGroup(`service:${serviceName}:method:${nameToken.value}`, path2, tokens, index);
@@ -12281,7 +12343,12 @@ function parseThriftSources(files) {
           const open = tokens.findIndex((candidate, candidateIndex) => candidateIndex > index && candidate.value === "{");
           if (open < 0)
             throw new ThriftSyntaxError(`${token.value} body is missing`, token.line, token.column);
-          document.types.push({ kind: token.value, name: name.value, locator: { path: path2, line: name.line, column: name.column } });
+          document.types.push({
+            kind: token.value,
+            name: name.value,
+            fields: thriftFields(tokens.slice(open + 1, matching(tokens, open, "{", "}"))),
+            locator: { path: path2, line: name.line, column: name.column }
+          });
           index = matching(tokens, open, "{", "}") + 1;
           if (tokens[index]?.value === "(") {
             const parsed = parseAnnotationGroup(`type:${name.value}`, path2, tokens, index);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@c4a/extract-thrift",
-  "version": "0.7.5",
+  "version": "0.7.9",
   "type": "module",
   "description": "Apache Thrift IDL catalog parser for Context",
   "license": "MIT",