@precisa-saude/fhir-pdf 0.26.1

package/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

package/README.md

@@ -0,0 +1,66 @@
+# @precisa-saude/fhir-pdf
+
+Extração da **camada de texto** de PDFs de laudo laboratorial, para alimentar a
+ancoragem do [`@precisa-saude/fhir-ocr-utils`](../ocr-utils).
+
+```bash
+npm i @precisa-saude/fhir-pdf
+```
+
+## Isto não é OCR
+
+A maior parte dos laudos que os laboratórios brasileiros entregam já vem com
+camada de texto, e ler essa camada é determinístico, offline e barato. Laudo
+digitalizado não tem camada nenhuma: aqui ele volta vazio, e a CLI diz isso em
+vez de devolver silêncio.
+
+Quem precisa de laudo digitalizado roda um OCR por fora e entrega o texto ao
+`fhir-ocr find`. O pacote não embute motor de reconhecimento: devolver lixo de
+OCR que a ancoragem depois trata como texto de verdade é pior do que devolver
+nada.
+
+## CLI
+
+```bash
+npx -p @precisa-saude/fhir-pdf fhir-pdf text laudo.pdf
+npx -p @precisa-saude/fhir-pdf fhir-pdf text laudo.pdf --json   # uma entrada por página
+```
+
+## Biblioteca
+
+```ts
+import { readFile } from 'node:fs/promises';
+
+import { extractPdfText } from '@precisa-saude/fhir-pdf';
+
+const { pages, text } = await extractPdfText(new Uint8Array(await readFile('laudo.pdf')));
+```
+
+## No fluxo completo
+
+```bash
+fhir-pdf  text laudo.pdf > laudo.txt          # camada de texto
+fhir-ocr  find laudo.txt                      # quais grandezas a página cita
+fhir-ocr  schema                              # o contrato que o modelo precisa devolver
+#                                               (o modelo roda onde você quiser)
+fhir-ocr  check saida.json --source laudo.txt --convert \
+  | fhir-bio convert | fhir-bio validate      # conferido e em FHIR R4
+```
+
+## Dependência
+
+`pdfjs-dist`, da Mozilla. É a exceção explícita à regra de dependência zero do
+ecossistema, e é o motivo de este pacote existir separado do `core` e do
+`ocr-utils`: os dois continuam sem dependência de runtime além do próprio
+catálogo.
+
+## Aviso médico
+
+Este pacote é uma ferramenta de software e **não** presta orientação médica. Os
+dados extraídos precisam de conferência profissional antes de qualquer uso
+clínico. Nenhum valor devolvido aqui foi interpretado por um profissional de
+saúde.
+
+## Licença
+
+Apache-2.0

package/dist/cli.js

@@ -0,0 +1,96 @@
+#!/usr/bin/env node
+
+// src/cli/index.ts
+import { readFile } from "fs/promises";
+import { parseArgs } from "util";
+import { exitWithError, outputJson, outputText } from "@precisa-saude/fhir/cli-utils";
+
+// src/extract-text.ts
+import { getDocument } from "pdfjs-dist/legacy/build/pdf.mjs";
+function joinItems(items) {
+  let out = "";
+  for (const item of items) {
+    out += item.str ?? "";
+    if (item.hasEOL) out += "\n";
+  }
+  return out;
+}
+async function extractPdfText(data) {
+  const doc = await getDocument({
+    data,
+    isEvalSupported: false,
+    useSystemFonts: false,
+    verbosity: 0
+  }).promise;
+  try {
+    const pages = [];
+    for (let n = 1; n <= doc.numPages; n += 1) {
+      const page = await doc.getPage(n);
+      const content = await page.getTextContent();
+      const items = content.items;
+      pages.push({ pageNumber: n, text: joinItems(items).trim() });
+    }
+    return {
+      pages,
+      text: pages.map((p) => p.text).filter(Boolean).join("\n\n")
+    };
+  } finally {
+    await doc.destroy();
+  }
+}
+
+// src/cli/index.ts
+var HELP = `fhir-pdf \u2014 CLI do @precisa-saude/fhir-pdf
+
+Uso: fhir-pdf text <arquivo.pdf> [--json]
+
+Comandos:
+  text <arquivo.pdf>      Extrair a camada de texto do PDF
+
+Flags:
+  --json                  Sa\xEDda em JSON, com uma entrada por p\xE1gina
+  --help, -h              Mostrar ajuda
+  --version, -v           Mostrar vers\xE3o
+
+N\xE3o faz OCR: laudo digitalizado n\xE3o tem camada de texto e sai vazio.
+`;
+async function main() {
+  const { positionals, values } = parseArgs({
+    allowPositionals: true,
+    options: {
+      help: { default: false, short: "h", type: "boolean" },
+      json: { default: false, type: "boolean" },
+      version: { default: false, short: "v", type: "boolean" }
+    },
+    strict: false
+  });
+  if (values.version) {
+    process.stdout.write(`${"0.26.1"}
+`);
+    return;
+  }
+  const [command, file] = positionals;
+  if (values.help || !command) {
+    process.stdout.write(HELP);
+    return;
+  }
+  if (command !== "text") {
+    exitWithError(`Comando desconhecido: ${command}
+Use --help para ver os comandos dispon\xEDveis.`);
+  }
+  if (!file) {
+    exitWithError("Informe o caminho do PDF. Exemplo: fhir-pdf text laudo.pdf");
+  }
+  const result = await extractPdfText(new Uint8Array(await readFile(file)));
+  if (values.json) {
+    outputJson(result);
+    return;
+  }
+  if (result.text === "") {
+    exitWithError(
+      "Este PDF n\xE3o tem camada de texto, provavelmente porque \xE9 digitalizado.\nRode um OCR por fora e passe o texto para o `fhir-ocr find`."
+    );
+  }
+  outputText(result.text);
+}
+main().catch((err) => exitWithError(err.message));

package/dist/index.cjs

@@ -0,0 +1,37 @@
+"use strict";Object.defineProperty(exports, "__esModule", {value: true}); function _nullishCoalesce(lhs, rhsFn) { if (lhs != null) { return lhs; } else { return rhsFn(); } }// src/extract-text.ts
+var _pdfmjs = require('pdfjs-dist/legacy/build/pdf.mjs');
+function joinItems(items) {
+  let out = "";
+  for (const item of items) {
+    out += _nullishCoalesce(item.str, () => ( ""));
+    if (item.hasEOL) out += "\n";
+  }
+  return out;
+}
+async function extractPdfText(data) {
+  const doc = await _pdfmjs.getDocument.call(void 0, {
+    data,
+    isEvalSupported: false,
+    useSystemFonts: false,
+    verbosity: 0
+  }).promise;
+  try {
+    const pages = [];
+    for (let n = 1; n <= doc.numPages; n += 1) {
+      const page = await doc.getPage(n);
+      const content = await page.getTextContent();
+      const items = content.items;
+      pages.push({ pageNumber: n, text: joinItems(items).trim() });
+    }
+    return {
+      pages,
+      text: pages.map((p) => p.text).filter(Boolean).join("\n\n")
+    };
+  } finally {
+    await doc.destroy();
+  }
+}
+
+
+exports.extractPdfText = extractPdfText;
+//# sourceMappingURL=index.cjs.map

package/dist/index.cjs.map

@@ -0,0 +1 @@
+{"version":3,"sources":["/home/runner/work/fhir-brasil/fhir-brasil/packages/pdf/dist/index.cjs","../src/extract-text.ts"],"names":[],"mappings":"AAAA;ACUA,yDAA4B;AAc5B,SAAS,SAAA,CAAU,KAAA,EAAqD;AACtE,EAAA,IAAI,IAAA,EAAM,EAAA;AACV,EAAA,IAAA,CAAA,MAAW,KAAA,GAAQ,KAAA,EAAO;AACxB,IAAA,IAAA,oBAAO,IAAA,CAAK,GAAA,UAAO,IAAA;AACnB,IAAA,GAAA,CAAI,IAAA,CAAK,MAAA,EAAQ,IAAA,GAAO,IAAA;AAAA,EAC1B;AACA,EAAA,OAAO,GAAA;AACT;AAmBA,MAAA,SAAsB,cAAA,CAAe,IAAA,EAAoC;AACvE,EAAA,MAAM,IAAA,EAAM,MAAM,iCAAA;AAAY,IAC5B,IAAA;AAAA,IACA,eAAA,EAAiB,KAAA;AAAA,IACjB,cAAA,EAAgB,KAAA;AAAA,IAChB,SAAA,EAAW;AAAA,EACb,CAAC,CAAA,CAAE,OAAA;AAEH,EAAA,IAAI;AACF,IAAA,MAAM,MAAA,EAAmB,CAAC,CAAA;AAC1B,IAAA,IAAA,CAAA,IAAS,EAAA,EAAI,CAAA,EAAG,EAAA,GAAK,GAAA,CAAI,QAAA,EAAU,EAAA,GAAK,CAAA,EAAG;AACzC,MAAA,MAAM,KAAA,EAAO,MAAM,GAAA,CAAI,OAAA,CAAQ,CAAC,CAAA;AAChC,MAAA,MAAM,QAAA,EAAU,MAAM,IAAA,CAAK,cAAA,CAAe,CAAA;AAC1C,MAAA,MAAM,MAAA,EAAQ,OAAA,CAAQ,KAAA;AACtB,MAAA,KAAA,CAAM,IAAA,CAAK,EAAE,UAAA,EAAY,CAAA,EAAG,IAAA,EAAM,SAAA,CAAU,KAAK,CAAA,CAAE,IAAA,CAAK,EAAE,CAAC,CAAA;AAAA,IAC7D;AAEA,IAAA,OAAO;AAAA,MACL,KAAA;AAAA,MACA,IAAA,EAAM,KAAA,CACH,GAAA,CAAI,CAAC,CAAA,EAAA,GAAM,CAAA,CAAE,IAAI,CAAA,CACjB,MAAA,CAAO,OAAO,CAAA,CACd,IAAA,CAAK,MAAM;AAAA,IAChB,CAAA;AAAA,EACF,EAAA,QAAE;AACA,IAAA,MAAM,GAAA,CAAI,OAAA,CAAQ,CAAA;AAAA,EACpB;AACF;AD5CA;AACE;AACF,wCAAC","file":"/home/runner/work/fhir-brasil/fhir-brasil/packages/pdf/dist/index.cjs","sourcesContent":[null,"/**\n * Camada de texto de um PDF de laudo.\n *\n * Isto **não é OCR**. A maior parte dos laudos que os laboratórios brasileiros\n * entregam já vem com camada de texto, e ler essa camada é determinístico,\n * offline e barato. Laudo digitalizado não tem camada nenhuma: aqui ele volta\n * vazio, e o consumidor decide se quer rodar um OCR por fora. Devolver string\n * vazia é melhor do que devolver lixo de reconhecimento que a ancoragem depois\n * trataria como se fosse texto de verdade.\n */\nimport { getDocument } from 'pdfjs-dist/legacy/build/pdf.mjs';\n\nexport interface PdfPage {\n  pageNumber: number;\n  text: string;\n}\n\nexport interface PdfText {\n  pages: PdfPage[];\n  /** As páginas com conteúdo, emendadas na ordem, separadas por linha em branco. */\n  text: string;\n}\n\n/** Junta os fragmentos de uma página preservando as quebras que o PDF marca. */\nfunction joinItems(items: { hasEOL?: boolean; str?: string }[]): string {\n  let out = '';\n  for (const item of items) {\n    out += item.str ?? '';\n    if (item.hasEOL) out += '\\n';\n  }\n  return out;\n}\n\n/**\n * Lê a camada de texto de um PDF em memória.\n *\n * `useSystemFonts` fica desligado porque o texto não depende de fonte para ser\n * extraído, e ligá-lo faz o pdf.js procurar fontes no sistema, o que muda o\n * resultado conforme a máquina.\n *\n * `isEvalSupported: false` desliga a avaliação de JavaScript embutido no PDF.\n * Laudo é documento de terceiro, então o parser não tem por que executar código\n * que veio junto, e desligar também tira uma fonte de variação entre máquinas.\n *\n * `verbosity: 0` não é cosmético. O pdf.js escreve aviso em `console.warn`, que\n * no Node cai no mesmo lugar que o resto, e laudo que usa fonte padrão não\n * embutida gera um aviso por página. Sem isto, os avisos entram no texto\n * extraído e a ancoragem passa a varrer mensagem de biblioteca junto com o\n * laudo. Apareceu num relatório real de 68 páginas, não no PDF de exemplo.\n */\nexport async function extractPdfText(data: Uint8Array): Promise<PdfText> {\n  const doc = await getDocument({\n    data,\n    isEvalSupported: false,\n    useSystemFonts: false,\n    verbosity: 0,\n  }).promise;\n\n  try {\n    const pages: PdfPage[] = [];\n    for (let n = 1; n <= doc.numPages; n += 1) {\n      const page = await doc.getPage(n);\n      const content = await page.getTextContent();\n      const items = content.items as { hasEOL?: boolean; str?: string }[];\n      pages.push({ pageNumber: n, text: joinItems(items).trim() });\n    }\n\n    return {\n      pages,\n      text: pages\n        .map((p) => p.text)\n        .filter(Boolean)\n        .join('\\n\\n'),\n    };\n  } finally {\n    await doc.destroy();\n  }\n}\n"]}

package/dist/index.d.cts

@@ -0,0 +1,29 @@
+interface PdfPage {
+    pageNumber: number;
+    text: string;
+}
+interface PdfText {
+    pages: PdfPage[];
+    /** As páginas com conteúdo, emendadas na ordem, separadas por linha em branco. */
+    text: string;
+}
+/**
+ * Lê a camada de texto de um PDF em memória.
+ *
+ * `useSystemFonts` fica desligado porque o texto não depende de fonte para ser
+ * extraído, e ligá-lo faz o pdf.js procurar fontes no sistema, o que muda o
+ * resultado conforme a máquina.
+ *
+ * `isEvalSupported: false` desliga a avaliação de JavaScript embutido no PDF.
+ * Laudo é documento de terceiro, então o parser não tem por que executar código
+ * que veio junto, e desligar também tira uma fonte de variação entre máquinas.
+ *
+ * `verbosity: 0` não é cosmético. O pdf.js escreve aviso em `console.warn`, que
+ * no Node cai no mesmo lugar que o resto, e laudo que usa fonte padrão não
+ * embutida gera um aviso por página. Sem isto, os avisos entram no texto
+ * extraído e a ancoragem passa a varrer mensagem de biblioteca junto com o
+ * laudo. Apareceu num relatório real de 68 páginas, não no PDF de exemplo.
+ */
+declare function extractPdfText(data: Uint8Array): Promise<PdfText>;
+
+export { type PdfPage, type PdfText, extractPdfText };

package/dist/index.d.ts

@@ -0,0 +1,29 @@
+interface PdfPage {
+    pageNumber: number;
+    text: string;
+}
+interface PdfText {
+    pages: PdfPage[];
+    /** As páginas com conteúdo, emendadas na ordem, separadas por linha em branco. */
+    text: string;
+}
+/**
+ * Lê a camada de texto de um PDF em memória.
+ *
+ * `useSystemFonts` fica desligado porque o texto não depende de fonte para ser
+ * extraído, e ligá-lo faz o pdf.js procurar fontes no sistema, o que muda o
+ * resultado conforme a máquina.
+ *
+ * `isEvalSupported: false` desliga a avaliação de JavaScript embutido no PDF.
+ * Laudo é documento de terceiro, então o parser não tem por que executar código
+ * que veio junto, e desligar também tira uma fonte de variação entre máquinas.
+ *
+ * `verbosity: 0` não é cosmético. O pdf.js escreve aviso em `console.warn`, que
+ * no Node cai no mesmo lugar que o resto, e laudo que usa fonte padrão não
+ * embutida gera um aviso por página. Sem isto, os avisos entram no texto
+ * extraído e a ancoragem passa a varrer mensagem de biblioteca junto com o
+ * laudo. Apareceu num relatório real de 68 páginas, não no PDF de exemplo.
+ */
+declare function extractPdfText(data: Uint8Array): Promise<PdfText>;
+
+export { type PdfPage, type PdfText, extractPdfText };

package/dist/index.js

@@ -0,0 +1,37 @@
+// src/extract-text.ts
+import { getDocument } from "pdfjs-dist/legacy/build/pdf.mjs";
+function joinItems(items) {
+  let out = "";
+  for (const item of items) {
+    out += item.str ?? "";
+    if (item.hasEOL) out += "\n";
+  }
+  return out;
+}
+async function extractPdfText(data) {
+  const doc = await getDocument({
+    data,
+    isEvalSupported: false,
+    useSystemFonts: false,
+    verbosity: 0
+  }).promise;
+  try {
+    const pages = [];
+    for (let n = 1; n <= doc.numPages; n += 1) {
+      const page = await doc.getPage(n);
+      const content = await page.getTextContent();
+      const items = content.items;
+      pages.push({ pageNumber: n, text: joinItems(items).trim() });
+    }
+    return {
+      pages,
+      text: pages.map((p) => p.text).filter(Boolean).join("\n\n")
+    };
+  } finally {
+    await doc.destroy();
+  }
+}
+export {
+  extractPdfText
+};
+//# sourceMappingURL=index.js.map

package/dist/index.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../src/extract-text.ts"],"sourcesContent":["/**\n * Camada de texto de um PDF de laudo.\n *\n * Isto **não é OCR**. A maior parte dos laudos que os laboratórios brasileiros\n * entregam já vem com camada de texto, e ler essa camada é determinístico,\n * offline e barato. Laudo digitalizado não tem camada nenhuma: aqui ele volta\n * vazio, e o consumidor decide se quer rodar um OCR por fora. Devolver string\n * vazia é melhor do que devolver lixo de reconhecimento que a ancoragem depois\n * trataria como se fosse texto de verdade.\n */\nimport { getDocument } from 'pdfjs-dist/legacy/build/pdf.mjs';\n\nexport interface PdfPage {\n  pageNumber: number;\n  text: string;\n}\n\nexport interface PdfText {\n  pages: PdfPage[];\n  /** As páginas com conteúdo, emendadas na ordem, separadas por linha em branco. */\n  text: string;\n}\n\n/** Junta os fragmentos de uma página preservando as quebras que o PDF marca. */\nfunction joinItems(items: { hasEOL?: boolean; str?: string }[]): string {\n  let out = '';\n  for (const item of items) {\n    out += item.str ?? '';\n    if (item.hasEOL) out += '\\n';\n  }\n  return out;\n}\n\n/**\n * Lê a camada de texto de um PDF em memória.\n *\n * `useSystemFonts` fica desligado porque o texto não depende de fonte para ser\n * extraído, e ligá-lo faz o pdf.js procurar fontes no sistema, o que muda o\n * resultado conforme a máquina.\n *\n * `isEvalSupported: false` desliga a avaliação de JavaScript embutido no PDF.\n * Laudo é documento de terceiro, então o parser não tem por que executar código\n * que veio junto, e desligar também tira uma fonte de variação entre máquinas.\n *\n * `verbosity: 0` não é cosmético. O pdf.js escreve aviso em `console.warn`, que\n * no Node cai no mesmo lugar que o resto, e laudo que usa fonte padrão não\n * embutida gera um aviso por página. Sem isto, os avisos entram no texto\n * extraído e a ancoragem passa a varrer mensagem de biblioteca junto com o\n * laudo. Apareceu num relatório real de 68 páginas, não no PDF de exemplo.\n */\nexport async function extractPdfText(data: Uint8Array): Promise<PdfText> {\n  const doc = await getDocument({\n    data,\n    isEvalSupported: false,\n    useSystemFonts: false,\n    verbosity: 0,\n  }).promise;\n\n  try {\n    const pages: PdfPage[] = [];\n    for (let n = 1; n <= doc.numPages; n += 1) {\n      const page = await doc.getPage(n);\n      const content = await page.getTextContent();\n      const items = content.items as { hasEOL?: boolean; str?: string }[];\n      pages.push({ pageNumber: n, text: joinItems(items).trim() });\n    }\n\n    return {\n      pages,\n      text: pages\n        .map((p) => p.text)\n        .filter(Boolean)\n        .join('\\n\\n'),\n    };\n  } finally {\n    await doc.destroy();\n  }\n}\n"],"mappings":";AAUA,SAAS,mBAAmB;AAc5B,SAAS,UAAU,OAAqD;AACtE,MAAI,MAAM;AACV,aAAW,QAAQ,OAAO;AACxB,WAAO,KAAK,OAAO;AACnB,QAAI,KAAK,OAAQ,QAAO;AAAA,EAC1B;AACA,SAAO;AACT;AAmBA,eAAsB,eAAe,MAAoC;AACvE,QAAM,MAAM,MAAM,YAAY;AAAA,IAC5B;AAAA,IACA,iBAAiB;AAAA,IACjB,gBAAgB;AAAA,IAChB,WAAW;AAAA,EACb,CAAC,EAAE;AAEH,MAAI;AACF,UAAM,QAAmB,CAAC;AAC1B,aAAS,IAAI,GAAG,KAAK,IAAI,UAAU,KAAK,GAAG;AACzC,YAAM,OAAO,MAAM,IAAI,QAAQ,CAAC;AAChC,YAAM,UAAU,MAAM,KAAK,eAAe;AAC1C,YAAM,QAAQ,QAAQ;AACtB,YAAM,KAAK,EAAE,YAAY,GAAG,MAAM,UAAU,KAAK,EAAE,KAAK,EAAE,CAAC;AAAA,IAC7D;AAEA,WAAO;AAAA,MACL;AAAA,MACA,MAAM,MACH,IAAI,CAAC,MAAM,EAAE,IAAI,EACjB,OAAO,OAAO,EACd,KAAK,MAAM;AAAA,IAChB;AAAA,EACF,UAAE;AACA,UAAM,IAAI,QAAQ;AAAA,EACpB;AACF;","names":[]}

package/package.json

@@ -0,0 +1,66 @@
+{
+  "name": "@precisa-saude/fhir-pdf",
+  "version": "0.26.1",
+  "description": "Extração da camada de texto de PDFs de laudo laboratorial, para alimentar a ancoragem do fhir-ocr-utils",
+  "keywords": [
+    "fhir",
+    "pdf",
+    "lab-results",
+    "text-extraction",
+    "brasil"
+  ],
+  "homepage": "https://github.com/Precisa-Saude/fhir-brasil/tree/main/packages/pdf#readme",
+  "bugs": "https://github.com/Precisa-Saude/fhir-brasil/issues",
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/Precisa-Saude/fhir-brasil.git",
+    "directory": "packages/pdf"
+  },
+  "license": "Apache-2.0",
+  "sideEffects": false,
+  "type": "module",
+  "exports": {
+    ".": {
+      "import": {
+        "types": "./dist/index.d.ts",
+        "default": "./dist/index.js"
+      },
+      "require": {
+        "types": "./dist/index.d.cts",
+        "default": "./dist/index.cjs"
+      }
+    }
+  },
+  "main": "./dist/index.cjs",
+  "module": "./dist/index.js",
+  "types": "./dist/index.d.ts",
+  "bin": {
+    "fhir-pdf": "./dist/cli.js"
+  },
+  "files": [
+    "dist"
+  ],
+  "dependencies": {
+    "pdfjs-dist": "^4.10.38",
+    "@precisa-saude/fhir": "^0.26.1"
+  },
+  "devDependencies": {
+    "tsup": "^8.3.5",
+    "typescript": "~5.7.3",
+    "vitest": "^2.1.8"
+  },
+  "engines": {
+    "node": ">=22"
+  },
+  "publishConfig": {
+    "access": "public"
+  },
+  "scripts": {
+    "build": "tsup",
+    "clean": "rm -rf dist .turbo",
+    "lint": "eslint src/ --max-warnings 0",
+    "test": "vitest run --passWithNoTests",
+    "test:coverage": "vitest run --coverage",
+    "typecheck": "tsc --noEmit"
+  }
+}