@pipeworx/mcp-guam-code 0.1.2 → 0.1.3

package/README.md

@@ -3,7 +3,7 @@
 Guam Code Annotated (GCA) — Guam territorial statutes, by citation and by
 topic/keyword search. Keyless.
 
-Part of [Pipeworx](https://pipeworx.io) — an MCP gateway connecting AI agents to 1815+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.
+Part of [Pipeworx](https://pipeworx.io) — an MCP gateway connecting AI agents to 1819+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.
 
 ## Tools
 
@@ -224,7 +224,7 @@ directly, instead of just this one's:
 }
 ```
 
-Both URLs reach the same gateway and the same 1815+ data sources. The
+Both URLs reach the same gateway and the same 1819+ data sources. The
 only difference is which pack's tools are listed **directly**; `ask_pipeworx`
 reaches all of them from either one.
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@pipeworx/mcp-guam-code",
-  "version": "0.1.2",
+  "version": "0.1.3",
   "description": "Guam Code Annotated (GCA) — section lookup and search. Fleet #2888.",
   "type": "module",
   "main": "src/index.ts",
@@ -26,7 +26,7 @@
     "@cloudflare/workers-types": "^4.20260405.1"
   },
   "pipeworx": {
-    "sourceHash": "v1-0e8b06ad75d31b79367ea7bccec933bfae1665a234e87b2fd47a9220c214f878",
-    "sourceCommit": "fe38188882d0fe91e5a45d82b7b989b4aae1e8b6"
+    "sourceHash": "v1-e101ffcf2c7ba1d5bce6f1a3825e124694dc1e346ebf10ef701f4239c45c5202",
+    "sourceCommit": "a03f96ed672b8c149593c64ecbf30280cabf084c"
   }
 }

package/server.json

@@ -3,7 +3,7 @@
   "name": "io.github.pipeworx-io/guam-code",
   "title": "Guam Code",
   "description": "Guam Code Annotated (GCA) — section lookup and search. Fleet #2888.",
-  "version": "0.1.2",
+  "version": "0.1.3",
   "websiteUrl": "https://pipeworx.io/packs/guam-code",
   "repository": {
     "url": "https://github.com/pipeworx-io/mcp-guam-code",

package/src/index.ts

@@ -1325,7 +1325,18 @@ async function extractPdfText(buf: ArrayBuffer, options?: PdfExtractOptions): Pr
 
   const TOKEN_RE =
     /\/(\S+)\s+[\d.]+\s+Tf|\[((?:\\.|[^\]])*)\]\s*TJ|<([0-9A-Fa-f\s]*)>\s*Tj|\(((?:\\.|[^()])*)\)\s*Tj|1\s+0\s+0\s+1\s+[\d.-]+\s+([\d.-]+)\s+Tm/g;
-  const TJ_PIECE_RE = /\(((?:\\.|[^()])*)\)|<([0-9A-Fa-f\s]*)>/g;
+  // Third alternative (bare number) added for Indonesia's JDIH statute PDFs
+  // (jdih.setneg.go.id, fleet #3121): that producer never writes a literal
+  // space byte between words — "REPUBLIK INDONESIA" is encoded as one TJ run
+  // `[(…K)-269.0(I)…]`, where the -269 IS the word gap, not kerning. Every
+  // sampled font's intra-word kerning tops out around +-30 (observed: 2.0,
+  // -2.9, -14.0, -24.0); the real word gaps in the same document measured
+  // -269, -286, -290, -692, -1396, -1400 — two clusters with nothing between
+  // them, so a flat threshold cleanly separates "kerning" from "space" without
+  // needing the current font size (the TJ number is already in thousandths of
+  // text space, before the Tfs/Th scale-up ISO 32000 §9.4.3 applies).
+  const TJ_PIECE_RE = /\(((?:\\.|[^()])*)\)|<([0-9A-Fa-f\s]*)>|(-?\d+(?:\.\d+)?)/g;
+  const TJ_WORD_GAP_THRESHOLD = -100;
 
   function decodeRun(dec: FontDecoder, literal: string | undefined, hex: string | undefined): string {
     if (literal !== undefined) {
@@ -1450,7 +1461,17 @@ async function extractPdfText(buf: ArrayBuffer, options?: PdfExtractOptions): Pr
       }
       const dec = (currentFont && fontMap.get(currentFont)) || { kind: 'winansi' as const };
       if (m[2] !== undefined) {
-        for (const piece of m[2].matchAll(TJ_PIECE_RE)) out += decodeRun(dec, piece[1], piece[2]);
+        for (const piece of m[2].matchAll(TJ_PIECE_RE)) {
+          if (piece[3] !== undefined) {
+            // A big negative adjustment between two TJ pieces with no
+            // literal space byte at all — see TJ_PIECE_RE's comment above.
+            // Skip if `out` already ends in whitespace so a producer that
+            // DOES write literal spaces never gets a doubled one.
+            if (parseFloat(piece[3]) <= TJ_WORD_GAP_THRESHOLD && !/\s$/.test(out)) out += ' ';
+            continue;
+          }
+          out += decodeRun(dec, piece[1], piece[2]);
+        }
       } else if (m[3] !== undefined) {
         out += decodeRun(dec, undefined, m[3]);
       } else if (m[4] !== undefined) {

package/src/server.ts

@@ -11,7 +11,7 @@ import * as bakedIndexModule from './gu-baked-data.js';
 const bakedIndex = Object.fromEntries(Object.entries(bakedIndexModule));
 
 const server = new Server(
-  { name: '@pipeworx/mcp-guam-code', version: '0.1.2' },
+  { name: '@pipeworx/mcp-guam-code', version: '0.1.3' },
   { capabilities: { tools: {} } },
 );