codetrellis 0.0.0-stage → 0.2.0

package/src/backend/services/material-reader/docx-markdown.js

@@ -0,0 +1,198 @@
+var __defProp = Object.defineProperty;
+var __getOwnPropDesc = Object.getOwnPropertyDescriptor;
+var __getOwnPropNames = Object.getOwnPropertyNames;
+var __hasOwnProp = Object.prototype.hasOwnProperty;
+var __export = (target, all) => {
+  for (var name in all)
+    __defProp(target, name, { get: all[name], enumerable: true });
+};
+var __copyProps = (to, from, except, desc) => {
+  if (from && typeof from === "object" || typeof from === "function") {
+    for (let key of __getOwnPropNames(from))
+      if (!__hasOwnProp.call(to, key) && key !== except)
+        __defProp(to, key, { get: () => from[key], enumerable: !(desc = __getOwnPropDesc(from, key)) || desc.enumerable });
+  }
+  return to;
+};
+var __toCommonJS = (mod) => __copyProps(__defProp({}, "__esModule", { value: true }), mod);
+var docx_markdown_exports = {};
+__export(docx_markdown_exports, {
+  docxHtmlToMarkdown: () => docxHtmlToMarkdown
+});
+module.exports = __toCommonJS(docx_markdown_exports);
+const ENTITIES = { amp: "&", lt: "<", gt: ">", quot: '"', apos: "'", nbsp: " " };
+function decode(s) {
+  return s.replace(/&(#x[0-9a-f]+|#\d+|[a-z]+);/gi, (m, e) => {
+    if (e[0] === "#") {
+      const n = e[1] === "x" || e[1] === "X" ? parseInt(e.slice(2), 16) : Number(e.slice(1));
+      return Number.isFinite(n) && n > 0 && n <= 1114111 ? String.fromCodePoint(n) : m;
+    }
+    return ENTITIES[e.toLowerCase()] ?? m;
+  });
+}
+function docxHtmlToMarkdown(html) {
+  const out = [];
+  const lists = [];
+  const tables = [];
+  let line = "";
+  let prefix = "";
+  const links = [];
+  const write = (s) => {
+    const t = tables[tables.length - 1];
+    if (t && t.cell !== null) t.cell += s;
+    else line += s;
+  };
+  const flush = (blank) => {
+    const text = line.replace(/[ \t]+/g, " ").trim();
+    if (text) out.push(prefix + text);
+    if (blank && out.length && out[out.length - 1] !== "") out.push("");
+    line = "";
+    prefix = "";
+  };
+  for (const m of html.matchAll(/<(\/?)([a-z][a-z0-9]*)\b([^>]*?)\/?>|([^<]+)/gi)) {
+    if (m[4] !== void 0) {
+      write(decode(m[4]));
+      continue;
+    }
+    const closing = m[1] === "/";
+    const tag = m[2].toLowerCase();
+    const attrs = m[3] ?? "";
+    const inCell = tables.length > 0 && tables[tables.length - 1].cell !== null;
+    switch (tag) {
+      case "h1":
+      case "h2":
+      case "h3":
+      case "h4":
+      case "h5":
+      case "h6":
+        if (inCell) {
+          if (closing) write(" ");
+          break;
+        }
+        if (closing) flush(true);
+        else {
+          flush(false);
+          prefix = `${"#".repeat(Number(tag[1]))} `;
+        }
+        break;
+      case "p":
+        if (inCell) {
+          if (closing) write(" ");
+          break;
+        }
+        if (closing) flush(lists.length === 0);
+        else if (lists.length === 0) flush(false);
+        break;
+      case "ul":
+      case "ol":
+        if (inCell) break;
+        if (closing) {
+          flush(false);
+          lists.pop();
+          if (lists.length === 0 && out.length && out[out.length - 1] !== "") out.push("");
+        } else {
+          flush(false);
+          lists.push({ ordered: tag === "ol", n: 0 });
+        }
+        break;
+      case "li": {
+        if (inCell) {
+          write(closing ? "; " : "");
+          break;
+        }
+        if (closing) {
+          flush(false);
+          break;
+        }
+        flush(false);
+        const l = lists[lists.length - 1];
+        const depth = Math.max(0, lists.length - 1);
+        prefix = `${"  ".repeat(depth)}${l?.ordered ? `${++l.n}.` : "-"} `;
+        break;
+      }
+      case "table":
+        if (!closing) {
+          if (!inCell) flush(true);
+          tables.push({ rows: [], row: null, cell: null });
+        } else {
+          const t = tables.pop();
+          if (!t) break;
+          if (tables.length > 0) {
+            write(t.rows.map((r) => r.join(", ")).join("; "));
+          } else {
+            out.push(...gfmTable(t.rows), "");
+          }
+        }
+        break;
+      case "tr": {
+        const t = tables[tables.length - 1];
+        if (!t) break;
+        if (closing) {
+          if (t.row) t.rows.push(t.row);
+          t.row = null;
+        } else t.row = [];
+        break;
+      }
+      case "td":
+      case "th": {
+        const t = tables[tables.length - 1];
+        if (!t) break;
+        if (closing) {
+          (t.row ??= []).push((t.cell ?? "").replace(/\s+/g, " ").trim());
+          t.cell = null;
+        } else t.cell = "";
+        break;
+      }
+      case "strong":
+      case "b":
+        write("**");
+        break;
+      case "em":
+      case "i":
+        write("_");
+        break;
+      case "s":
+      case "del":
+        write("~~");
+        break;
+      case "br":
+        if (inCell) write(" ");
+        else {
+          flush(false);
+        }
+        break;
+      case "a": {
+        if (!closing) {
+          const href = attrs.match(/\bhref="([^"]*)"/)?.[1];
+          links.push(href ? decode(href) : null);
+          if (href) write("[");
+        } else {
+          const href = links.pop();
+          if (href) write(`](${href})`);
+        }
+        break;
+      }
+      case "img": {
+        const alt = attrs.match(/\balt="([^"]*)"/)?.[1];
+        write(alt ? `[image: ${decode(alt)}]` : "[image]");
+        break;
+      }
+      default:
+        break;
+    }
+  }
+  flush(false);
+  while (out.length && out[out.length - 1] === "") out.pop();
+  return out.join("\n");
+}
+function gfmTable(rows) {
+  if (rows.length === 0) return [];
+  const width = Math.max(...rows.map((r) => r.length));
+  const cell = (s) => (s ?? "").replace(/\|/g, "\\|");
+  const line = (r) => `| ${Array.from({ length: width }, (_, i) => cell(r[i])).join(" | ")} |`;
+  return [line(rows[0]), `| ${Array.from({ length: width }, () => "---").join(" | ")} |`, ...rows.slice(1).map(line)];
+}
+// Annotate the CommonJS export names for ESM import in node:
+0 && (module.exports = {
+  docxHtmlToMarkdown
+});

package/src/backend/services/material-reader/fixtures.test-helper.js

@@ -0,0 +1,169 @@
+var __create = Object.create;
+var __defProp = Object.defineProperty;
+var __getOwnPropDesc = Object.getOwnPropertyDescriptor;
+var __getOwnPropNames = Object.getOwnPropertyNames;
+var __getProtoOf = Object.getPrototypeOf;
+var __hasOwnProp = Object.prototype.hasOwnProperty;
+var __export = (target, all) => {
+  for (var name in all)
+    __defProp(target, name, { get: all[name], enumerable: true });
+};
+var __copyProps = (to, from, except, desc) => {
+  if (from && typeof from === "object" || typeof from === "function") {
+    for (let key of __getOwnPropNames(from))
+      if (!__hasOwnProp.call(to, key) && key !== except)
+        __defProp(to, key, { get: () => from[key], enumerable: !(desc = __getOwnPropDesc(from, key)) || desc.enumerable });
+  }
+  return to;
+};
+var __toESM = (mod, isNodeMode, target) => (target = mod != null ? __create(__getProtoOf(mod)) : {}, __copyProps(
+  // If the importer is in node compatibility mode or this is not an ESM
+  // file that has been converted to a CommonJS file using a Babel-
+  // compatible transform (i.e. "__esModule" has not been set), then set
+  // "default" to the CommonJS "module.exports" for node compatibility.
+  isNodeMode || !mod || !mod.__esModule ? __defProp(target, "default", { value: mod, enumerable: true }) : target,
+  mod
+));
+var __toCommonJS = (mod) => __copyProps(__defProp({}, "__esModule", { value: true }), mod);
+var fixtures_test_helper_exports = {};
+__export(fixtures_test_helper_exports, {
+  makeDeck: () => makeDeck,
+  makeDocx: () => makeDocx,
+  makePdf: () => makePdf,
+  makeWorkbook: () => makeWorkbook,
+  makeZip: () => makeZip
+});
+module.exports = __toCommonJS(fixtures_test_helper_exports);
+var import_node_zlib = __toESM(require("node:zlib"));
+function makeZip(entries) {
+  const locals = [];
+  const centrals = [];
+  let offset = 0;
+  Object.entries(entries).forEach(([name, content], i) => {
+    const raw = Buffer.isBuffer(content) ? content : Buffer.from(content, "utf8");
+    const method = i === 0 ? 0 : 8;
+    const data = method === 0 ? raw : import_node_zlib.default.deflateRawSync(raw);
+    const nameBuf = Buffer.from(name, "utf8");
+    const local = Buffer.alloc(30);
+    local.writeUInt32LE(67324752, 0);
+    local.writeUInt16LE(20, 4);
+    local.writeUInt16LE(method, 8);
+    local.writeUInt32LE(import_node_zlib.default.crc32(raw), 14);
+    local.writeUInt32LE(data.length, 18);
+    local.writeUInt32LE(raw.length, 22);
+    local.writeUInt16LE(nameBuf.length, 26);
+    const central = Buffer.alloc(46);
+    central.writeUInt32LE(33639248, 0);
+    central.writeUInt16LE(20, 4);
+    central.writeUInt16LE(20, 6);
+    central.writeUInt16LE(method, 10);
+    central.writeUInt32LE(import_node_zlib.default.crc32(raw), 16);
+    central.writeUInt32LE(data.length, 20);
+    central.writeUInt32LE(raw.length, 24);
+    central.writeUInt16LE(nameBuf.length, 28);
+    central.writeUInt32LE(offset, 42);
+    locals.push(local, nameBuf, data);
+    centrals.push(central, nameBuf);
+    offset += 30 + nameBuf.length + data.length;
+  });
+  const cd = Buffer.concat(centrals);
+  const eocd = Buffer.alloc(22);
+  eocd.writeUInt32LE(101010256, 0);
+  eocd.writeUInt16LE(Object.keys(entries).length, 8);
+  eocd.writeUInt16LE(Object.keys(entries).length, 10);
+  eocd.writeUInt32LE(cd.length, 12);
+  eocd.writeUInt32LE(offset, 16);
+  return Buffer.concat([...locals, cd, eocd]);
+}
+const esc = (s) => s.replace(/&/g, "&amp;").replace(/</g, "&lt;").replace(/>/g, "&gt;").replace(/"/g, "&quot;");
+function makeWorkbook(sheets, opts = {}) {
+  const shared = [];
+  const names = Object.keys(sheets);
+  const col = (n) => {
+    let s = "";
+    for (let x = n; x > 0; x = Math.floor((x - 1) / 26)) s = String.fromCharCode(65 + (x - 1) % 26) + s;
+    return s;
+  };
+  const parts = {
+    "xl/workbook.xml": `<workbook xmlns:r="r"><sheets>${names.map((n, i) => `<sheet name="${esc(n)}" sheetId="${i + 1}" r:id="rId${i + 1}"/>`).join("")}</sheets></workbook>`,
+    "xl/_rels/workbook.xml.rels": `<Relationships>${names.map((_, i) => `<Relationship Id="rId${i + 1}" Target="worksheets/sheet${i + 1}.xml"/>`).join("")}</Relationships>`
+  };
+  names.forEach((name, i) => {
+    const rows = sheets[name];
+    const width = Math.max(1, ...rows.map((r) => r.length));
+    const cells = rows.map((r, ri) => `<row r="${ri + 1}">${r.map((v, ci) => {
+      const ref = `${col(ci + 1)}${ri + 1}`;
+      if (typeof v === "number") return `<c r="${ref}"><v>${v}</v></c>`;
+      shared.push(v);
+      return `<c r="${ref}" t="s"><v>${shared.length - 1}</v></c>`;
+    }).join("")}</row>`).join("");
+    parts[`xl/worksheets/sheet${i + 1}.xml`] = `<worksheet><dimension ref="A1:${col(width)}${Math.max(1, rows.length)}"/><sheetData>${cells}</sheetData></worksheet>`;
+  });
+  parts["xl/sharedStrings.xml"] = `<sst>${shared.map((s) => `<si><t>${esc(s)}</t></si>`).join("")}</sst>`;
+  if (opts.macros) parts["xl/vbaProject.bin"] = Buffer.from("not really a macro");
+  return makeZip(parts);
+}
+function makeDocx(paragraphs, table) {
+  const p = (t) => t.startsWith("# ") ? `<w:p><w:pPr><w:pStyle w:val="Heading1"/></w:pPr><w:r><w:t>${esc(t.slice(2))}</w:t></w:r></w:p>` : `<w:p><w:r><w:t xml:space="preserve">${esc(t)}</w:t></w:r></w:p>`;
+  const tbl = table ? `<w:tbl>${table.map((r) => `<w:tr>${r.map((c) => `<w:tc><w:p><w:r><w:t>${esc(c)}</w:t></w:r></w:p></w:tc>`).join("")}</w:tr>`).join("")}</w:tbl>` : "";
+  return makeZip({
+    "[Content_Types].xml": '<?xml version="1.0"?><Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types"><Default Extension="xml" ContentType="application/xml"/><Override PartName="/word/document.xml" ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.document.main+xml"/></Types>',
+    "_rels/.rels": '<?xml version="1.0"?><Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships"><Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument" Target="word/document.xml"/></Relationships>',
+    "word/document.xml": `<?xml version="1.0"?><w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main"><w:body>${paragraphs.map(p).join("")}${tbl}</w:body></w:document>`
+  });
+}
+function makeDeck(slides) {
+  const parts = {
+    "ppt/presentation.xml": `<p:presentation><p:sldIdLst>${slides.map((_, i) => `<p:sldId id="${256 + i}" r:id="rId${i + 1}"/>`).join("")}</p:sldIdLst></p:presentation>`,
+    "ppt/_rels/presentation.xml.rels": `<Relationships>${slides.map((_, i) => `<Relationship Id="rId${i + 1}" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/slide" Target="slides/slide${i + 1}.xml"/>`).join("")}</Relationships>`
+  };
+  slides.forEach(([title, ...lines], i) => {
+    parts[`ppt/slides/slide${i + 1}.xml`] = `<p:sld><p:cSld><p:spTree><p:sp><p:nvSpPr><p:nvPr><p:ph type="title"/></p:nvPr></p:nvSpPr><p:txBody><a:p><a:r><a:t>${esc(title)}</a:t></a:r></a:p></p:txBody></p:sp><p:sp><p:txBody>${lines.map((l) => `<a:p><a:r><a:t>${esc(l)}</a:t></a:r></a:p>`).join("")}</p:txBody></p:sp></p:spTree></p:cSld></p:sld>`;
+  });
+  return makeZip(parts);
+}
+function makePdf(pages) {
+  const objects = [];
+  const kids = pages.map((_, i) => `${4 + i * 2} 0 R`).join(" ");
+  objects.push("<< /Type /Catalog /Pages 2 0 R >>");
+  objects.push(`<< /Type /Pages /Kids [${kids}] /Count ${pages.length} >>`);
+  objects.push("<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica >>");
+  pages.forEach((text, i) => {
+    const stream = `BT /F1 18 Tf 72 720 Td (${text.replace(/[\\()]/g, (c) => `\\${c}`)}) Tj ET`;
+    objects.push(`<< /Type /Page /Parent 2 0 R /MediaBox [0 0 612 792] /Resources << /Font << /F1 3 0 R >> >> /Contents ${5 + i * 2} 0 R >>`);
+    objects.push(`<< /Length ${stream.length} >>
+stream
+${stream}
+endstream`);
+  });
+  let out = "%PDF-1.4\n";
+  const offsets = [];
+  objects.forEach((o, i) => {
+    offsets.push(out.length);
+    out += `${i + 1} 0 obj
+${o}
+endobj
+`;
+  });
+  const xref = out.length;
+  out += `xref
+0 ${objects.length + 1}
+0000000000 65535 f 
+${offsets.map((o) => `${String(o).padStart(10, "0")} 00000 n 
+`).join("")}`;
+  out += `trailer
+<< /Size ${objects.length + 1} /Root 1 0 R >>
+startxref
+${xref}
+%%EOF
+`;
+  return Buffer.from(out, "latin1");
+}
+// Annotate the CommonJS export names for ESM import in node:
+0 && (module.exports = {
+  makeDeck,
+  makeDocx,
+  makePdf,
+  makeWorkbook,
+  makeZip
+});

package/src/backend/services/material-reader/quote.js

@@ -0,0 +1,44 @@
+var __defProp = Object.defineProperty;
+var __getOwnPropDesc = Object.getOwnPropertyDescriptor;
+var __getOwnPropNames = Object.getOwnPropertyNames;
+var __hasOwnProp = Object.prototype.hasOwnProperty;
+var __export = (target, all) => {
+  for (var name in all)
+    __defProp(target, name, { get: all[name], enumerable: true });
+};
+var __copyProps = (to, from, except, desc) => {
+  if (from && typeof from === "object" || typeof from === "function") {
+    for (let key of __getOwnPropNames(from))
+      if (!__hasOwnProp.call(to, key) && key !== except)
+        __defProp(to, key, { get: () => from[key], enumerable: !(desc = __getOwnPropDesc(from, key)) || desc.enumerable });
+  }
+  return to;
+};
+var __toCommonJS = (mod) => __copyProps(__defProp({}, "__esModule", { value: true }), mod);
+var quote_exports = {};
+__export(quote_exports, {
+  fenceFor: () => fenceFor,
+  quoteMaterial: () => quoteMaterial
+});
+module.exports = __toCommonJS(quote_exports);
+const LANG = { csv: "csv", markdown: "markdown", text: "text" };
+function fenceFor(body) {
+  let longest = 0;
+  for (const m of body.matchAll(/`+/g)) longest = Math.max(longest, m[0].length);
+  return "`".repeat(Math.max(3, longest + 1));
+}
+function quoteMaterial(name, format, sections) {
+  if (sections.length === 0) return `Quoted from ${name}: (nothing in the part asked for)`;
+  return sections.map((s) => {
+    const fence = fenceFor(s.body);
+    return `Quoted from ${name} \u2014 ${s.heading}:
+${fence}${LANG[format] ?? "text"}
+${s.body}
+${fence}`;
+  }).join("\n\n");
+}
+// Annotate the CommonJS export names for ESM import in node:
+0 && (module.exports = {
+  fenceFor,
+  quoteMaterial
+});