diff --git a/README.md b/README.md index 4aa4689..548f104 100644 --- a/README.md +++ b/README.md @@ -9,6 +9,12 @@ pdf2html helps to convert PDF file to HTML or Text using [Apache Tika](https://tika.apache.org/). This module also helps to generate thumbnail image for PDF file using [Apache PDFBox](https://pdfbox.apache.org/). ### Installation +via yarn: + +``` +yarn add pdf2html +``` + via npm: ``` diff --git a/test/test.js b/test/test.js index f9bf6b5..ad69ccf 100644 --- a/test/test.js +++ b/test/test.js @@ -4,31 +4,38 @@ const should = chai.should() const pdf2html = require('../index') const pdfFilepath = __dirname + '/../sample.pdf' const pdfInvalidFilepath = __dirname + '/../sample2.pdf' -const pdfFileHTML = '\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n

\n

A Simple PDF File \n This is a small demonstration .pdf file - \n

\n

just for use in the Virtual Mechanics tutorials. More text. And more \n text. And more text. And more text. And more text. \n

\n

And more text. And more text. And more text. And more text. And more \n text. And more text. Boring, zzzzz. And more text. And more text. And \n more text. And more text. And more text. And more text. And more text. \n And more text. And more text. \n

\n

And more text. And more text. And more text. And more text. And more \n text. And more text. And more text. Even more. Continued on page 2 ...

\n

\n

\n

\n

Simple PDF File 2 \n ...continued from page 1. Yet more text. And more text. And more text. \n And more text. And more text. And more text. And more text. And more \n text. Oh, how boring typing this stuff. But not as boring as watching \n paint dry. And more text. And more text. And more text. And more text. \n Boring. More, a little more text. The end, and just as well.

\n

\n

\n' +const pdfFileHTML = '\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n

\n

A Simple PDF File \n This is a small demonstration .pdf file - \n

\n

just for use in the Virtual Mechanics tutorials. More text. And more \n text. And more text. And more text. And more text. \n

\n

And more text. And more text. And more text. And more text. And more \n text. And more text. Boring, zzzzz. And more text. And more text. And \n more text. And more text. And more text. And more text. And more text. \n And more text. And more text. \n

\n

And more text. And more text. And more text. And more text. And more \n text. And more text. And more text. Even more. Continued on page 2 ...

\n

\n

\n

\n

Simple PDF File 2 \n ...continued from page 1. Yet more text. And more text. And more text. \n And more text. And more text. And more text. And more text. And more \n text. Oh, how boring typing this stuff. But not as boring as watching \n paint dry. And more text. And more text. And more text. And more text. \n Boring. More, a little more text. The end, and just as well.

\n

\n

\n' const pdfFileText = '\n A Simple PDF File \n This is a small demonstration .pdf file - \n\n just for use in the Virtual Mechanics tutorials. More text. And more \n text. And more text. And more text. And more text. \n\n And more text. And more text. And more text. And more text. And more \n text. And more text. Boring, zzzzz. And more text. And more text. And \n more text. And more text. And more text. And more text. And more text. \n And more text. And more text. \n\n And more text. And more text. And more text. And more text. And more \n text. And more text. And more text. Even more. Continued on page 2 ...\n\n\n\n Simple PDF File 2 \n ...continued from page 1. Yet more text. And more text. And more text. \n And more text. And more text. And more text. And more text. And more \n text. Oh, how boring typing this stuff. But not as boring as watching \n paint dry. And more text. And more text. And more text. And more text. \n Boring. More, a little more text. The end, and just as well. \n\n\n' const pdfFileMeta = { - "Content-Length": "3028", - "Content-Type": "application/pdf", - "Creation-Date": "2006-03-01T07:28:26Z", - "X-Parsed-By": ["org.apache.tika.parser.DefaultParser", "org.apache.tika.parser.pdf.PDFParser"], - "access_permission:assemble_document": "true", - "access_permission:can_modify": "true", - "access_permission:can_print": "true", - "access_permission:can_print_degraded": "true", - "access_permission:extract_content": "true", - "access_permission:extract_for_accessibility": "true", - "access_permission:fill_in_form": "true", - "access_permission:modify_annotations": "true", - "created": "Wed Mar 01 07:28:26 UTC 2006", - "dc:format": "application/pdf; version=1.3", - "dcterms:created": "2006-03-01T07:28:26Z", - "meta:creation-date": "2006-03-01T07:28:26Z", - "pdf:PDFVersion": "1.3", - "pdf:encrypted": "false", - "producer": "Nevrona Designs", - "resourceName": "sample.pdf", - "xmp:CreatorTool": "Rave (http://www.nevrona.com/rave)", - "xmpTPg:NPages": "2" + 'Content-Length': '3028', + 'Content-Type': 'application/pdf', + 'Creation-Date': '2006-03-01T07:28:26Z', + 'X-Parsed-By': + ['org.apache.tika.parser.DefaultParser', + 'org.apache.tika.parser.pdf.PDFParser'], + 'access_permission:assemble_document': 'true', + 'access_permission:can_modify': 'true', + 'access_permission:can_print': 'true', + 'access_permission:can_print_degraded': 'true', + 'access_permission:extract_content': 'true', + 'access_permission:extract_for_accessibility': 'true', + 'access_permission:fill_in_form': 'true', + 'access_permission:modify_annotations': 'true', + created: '2006-03-01T07:28:26Z', + 'dc:format': 'application/pdf; version=1.3', + 'dcterms:created': '2006-03-01T07:28:26Z', + 'meta:creation-date': '2006-03-01T07:28:26Z', + 'pdf:PDFVersion': '1.3', + 'pdf:charsPerPage': ['569', '367'], + 'pdf:docinfo:created': '2006-03-01T07:28:26Z', + 'pdf:docinfo:creator_tool': 'Rave (http://www.nevrona.com/rave)', + 'pdf:docinfo:producer': 'Nevrona Designs', + 'pdf:encrypted': 'false', + 'pdf:unmappedUnicodeCharsPerPage': ['0', '0'], + producer: 'Nevrona Designs', + resourceName: 'sample.pdf', + 'xmp:CreatorTool': 'Rave (http://www.nevrona.com/rave)', + 'xmpTPg:NPages': '2' } describe('PDF to HTML', function () {