@pdfme/pdf-lib 0.0.0

package/__tests__/utils/unicode.spec.ts

@@ -0,0 +1,337 @@
+import {
+  mergeIntoTypedArray,
+  utf16Encode,
+  utf8Encode,
+  utf16Decode,
+} from '../../src/utils';
+
+const utf8BOM = new Uint8Array([0xef, 0xbb, 0xbf]);
+const utf16BOM = new Uint16Array([0xfeff]);
+
+const withUtf8Bom = (encoding: Uint8Array) =>
+  mergeIntoTypedArray(utf8BOM, encoding);
+
+const withUtf16Bom = (encoding: Uint16Array) =>
+  new Uint16Array([...Array.from(utf16BOM), ...Array.from(encoding)]);
+
+describe(`utf8Encode`, () => {
+  it(`encodes <U+004D U+0430 U+4E8C U+10302> to UTF-8`, () => {
+    const input = '\u{004D}\u{0430}\u{4E8C}\u{10302}';
+
+    // prettier-ignore
+    const expected = new Uint8Array([
+      /* U+004D  */ 0x4d, 
+      /* U+0430  */ 0xd0, 0xb0, 
+      /* U+4E8C  */ 0xe4, 0xba, 0x8c,
+      /* U+10302 */ 0xf0, 0x90, 0x8c, 0x82,
+    ]);
+
+    const actual = utf8Encode(input);
+
+    expect(actual).toEqual(withUtf8Bom(expected));
+  });
+
+  it(`encodes <U+004D U+0061 U+10000> to UTF-8`, () => {
+    const input = '\u{004D}\u{0061}\u{10000}';
+
+    // prettier-ignore
+    const expected = new Uint8Array([
+      /* U+004D  */ 0x4d, 
+      /* U+0061  */ 0x61, 
+      /* U+10000 */ 0xf0, 0x90, 0x80, 0x80,
+    ]);
+
+    const actual = utf8Encode(input);
+
+    expect(actual).toEqual(withUtf8Bom(expected));
+  });
+
+  it(`encodes <U+1F4A9 U+1F382> to UTF-8 (without a BOM)`, () => {
+    const input = '💩🎂';
+
+    // prettier-ignore
+    const expected = new Uint8Array([
+      /* U+1F4A9 */ 0xf0, 0x9f, 0x92, 0xa9, 
+      /* U+1F382 */ 0xf0, 0x9f, 0x8e, 0x82, 	
+    ]);
+
+    const actual = utf8Encode(input, false);
+
+    expect(actual).toEqual(expected);
+  });
+
+  it(`encodes "Дмитрий Козлюк (Dmitry Kozlyuk)" to UTF-8`, () => {
+    const input = 'Дмитрий Козлюк (Dmitry Kozlyuk)';
+
+    // prettier-ignore
+    const expected = new Uint8Array([
+      0xd0, 0x94, 0xd0, 0xbc, 0xd0, 0xb8, 0xd1, 0x82, 0xd1, 0x80, 0xd0, 0xb8,
+      0xd0, 0xb9, 0x20, 0xd0, 0x9a, 0xd0, 0xbe, 0xd0, 0xb7, 0xd0, 0xbb, 0xd1,
+      0x8e, 0xd0, 0xba, 0x20, 0x28, 0x44, 0x6d, 0x69, 0x74, 0x72, 0x79, 0x20,
+      0x4b, 0x6f, 0x7a, 0x6c, 0x79, 0x75, 0x6b, 0x29,
+    ]);
+
+    const actual = utf8Encode(input);
+
+    expect(actual).toEqual(withUtf8Bom(expected));
+  });
+
+  it(`encodes "ä☺𠜎️☁️" to UTF-8 (without a BOM)`, () => {
+    const input = 'ä☺𠜎️☁️';
+
+    // prettier-ignore
+    const expected = new Uint8Array([
+      0xc3, 0xa4, 0xe2, 0x98, 0xba, 0xf0, 0xa0, 0x9c, 0x8e, 0xef, 0xb8, 0x8f,
+      0xe2, 0x98, 0x81, 0xef, 0xb8, 0x8f,
+    ]);
+
+    const actual = utf8Encode(input, false);
+
+    expect(actual).toEqual(expected);
+  });
+});
+
+describe(`utf16Encode`, () => {
+  it(`encodes <U+004D U+0430 U+4E8C U+10302> to UTF-16`, () => {
+    const input = '\u{004D}\u{0430}\u{4E8C}\u{10302}';
+
+    // prettier-ignore
+    const expected = new Uint16Array(new Uint8Array([
+      /* U+004D  */ 0x4d, 0x00, 
+      /* U+0430  */ 0x30, 0x04,
+      /* U+4E8C  */ 0x8c, 0x4e,
+      /* U+10302 */ 0x00, 0xd8, 0x02, 0xdf, 
+    ]).buffer);
+
+    const actual = utf16Encode(input);
+
+    expect(actual).toEqual(withUtf16Bom(expected));
+  });
+
+  it(`encodes <U+004D U+0061 U+10000> to UTF-16`, () => {
+    const input = '\u{004D}\u{0061}\u{10000}';
+
+    // prettier-ignore
+    const expected = new Uint16Array(new Uint8Array([
+      /* U+004D  */ 0x4d, 0x00, 
+      /* U+0061  */ 0x61, 0x00,
+      /* U+10000 */ 0x00, 0xd8, 0x00, 0xdc,
+    ]).buffer);
+
+    const actual = utf16Encode(input);
+
+    expect(actual).toEqual(withUtf16Bom(expected));
+  });
+
+  it(`encodes <U+1F4A9 U+1F382> to UTF-16 (without a BOM)`, () => {
+    const input = '💩🎂';
+
+    // prettier-ignore
+    const expected = new Uint16Array(new Uint8Array([
+      /* U+1F4A9 */ 0x3d, 0xd8, 0xa9, 0xdc,
+      /* U+1F382 */ 0x3c, 0xd8, 0x82, 0xdf,
+    ]).buffer);
+
+    const actual = utf16Encode(input, false);
+
+    expect(actual).toEqual(expected);
+  });
+
+  it(`encodes "Дмитрий Козлюк (Dmitry Kozlyuk)" to UTF-16`, () => {
+    const input = 'Дмитрий Козлюк (Dmitry Kozlyuk)';
+
+    // prettier-ignore
+    const expected = new Uint16Array([
+      0x414, 0x43c, 0x438, 0x442, 0x440, 0x438, 0x439, 0x20, 0x41a, 0x43e, 
+      0x437, 0x43b, 0x44e, 0x43a, 0x20, 0x28, 0x44, 0x6d, 0x69, 0x74, 0x72, 
+      0x79, 0x20, 0x4b, 0x6f, 0x7a, 0x6c, 0x79, 0x75, 0x6b, 0x29,
+    ]);
+
+    const actual = utf16Encode(input);
+
+    expect(actual).toEqual(withUtf16Bom(expected));
+  });
+
+  it(`encodes "ä☺𠜎️☁️" to UTF-16 (without a BOM)`, () => {
+    const input = 'ä☺𠜎️☁️';
+
+    // prettier-ignore
+    const expected = new Uint16Array([
+      0xe4, 0x263a, 55361, 57102, 0xfe0f, 0x2601, 0xfe0f,
+    ]);
+
+    const actual = utf16Encode(input, false);
+
+    expect(actual).toEqual(expected);
+  });
+});
+
+describe(`utf16Decode`, () => {
+  it(`decodes <U+004D U+0430 U+4E8C U+10302> from UTF-16`, () => {
+    // prettier-ignore
+    const input = new Uint8Array([
+      /* U+004D  */ 0x00, 0x4d,
+      /* U+0430  */ 0x04, 0x30,
+      /* U+4E8C  */ 0x4e, 0x8c,
+      /* U+10302 */ 0xd8, 0x00, 0xdf, 0x02,
+    ]);
+
+    const expected = '\u{004D}\u{0430}\u{4E8C}\u{10302}';
+
+    const actual = utf16Decode(input, false);
+
+    expect(actual).toEqual(expected);
+  });
+
+  it(`decodes <U+004D U+0061 U+10000> from UTF-16`, () => {
+    // prettier-ignore
+    const input = new Uint8Array([
+      /* U+004D  */ 0x00, 0x4d, 
+      /* U+0061  */ 0x00, 0x61, 
+      /* U+10000 */ 0xd8, 0x00, 0xdc, 0x00,
+    ]);
+
+    const expected = '\u{004D}\u{0061}\u{10000}';
+
+    const actual = utf16Decode(input, false);
+
+    expect(actual).toEqual(expected);
+  });
+
+  it(`decodes <U+1F4A9 U+1F382> from UTF-16`, () => {
+    // prettier-ignore
+    const input = new Uint8Array([
+      /* U+1F4A9 */ 0xd8, 0x3d, 0xdc, 0xa9,
+      /* U+1F382 */ 0xd8, 0x3c, 0xdf, 0x82, 
+    ]);
+
+    const expected = '💩🎂';
+
+    const actual = utf16Decode(input, false);
+
+    expect(actual).toEqual(expected);
+  });
+
+  it(`decodes 'abcd' from UTF-16`, () => {
+    // prettier-ignore
+    const input = new Uint8Array([
+      /* a */ 0, 97,
+      /* b */ 0, 98,
+      /* c */ 0, 99,
+      /* d */ 0, 100,
+    ]);
+
+    const expected = 'abcd';
+
+    const actual = utf16Decode(input, false);
+
+    expect(actual).toEqual(expected);
+  });
+
+  it(`decodes "Дмитрий Козлюк (Dmitry Kozlyuk)" from UTF-16`, () => {
+    const littleEndianBOM = (0xfe << 8) | 0xff;
+
+    // prettier-ignore
+    const input = new Uint8Array(new Uint16Array([
+      littleEndianBOM,
+      0x414, 0x43c, 0x438, 0x442, 0x440, 0x438, 0x439, 0x020, 0x41a, 0x43e,
+      0x437, 0x43b, 0x44e, 0x43a, 0x020, 0x028, 0x044, 0x06d, 0x069, 0x074, 
+      0x072, 0x079, 0x020, 0x04b, 0x06f, 0x07a, 0x06c, 0x079, 0x075, 0x06b, 
+      0x29,
+    ]).buffer);
+
+    const expected = 'Дмитрий Козлюк (Dmitry Kozlyuk)';
+
+    const actual = utf16Decode(input, true);
+
+    expect(actual).toEqual(expected);
+  });
+
+  it(`decodes "ä☺𠜎️☁️" from UTF-16 (without a BOM)`, () => {
+    const littleEndianBOM = (0xfe << 8) | 0xff;
+
+    // prettier-ignore
+    const input = new Uint8Array(new Uint16Array([
+      littleEndianBOM,
+      0xe4, 0x263a, 55361, 57102, 0xfe0f, 0x2601, 0xfe0f,
+    ]).buffer);
+
+    const expected = 'ä☺𠜎️☁️';
+
+    const actual = utf16Decode(input, true);
+
+    expect(actual).toEqual(expected);
+  });
+
+  it(`injects a replacement character when the input ends prematurely`, () => {
+    // prettier-ignore
+    const input = new Uint8Array([
+      /* U+1F4A9 */ 0xd8, 0x3d, 0xdc, 0xa9,
+      /* U+1F382 */ 0xd8, 
+    ]);
+
+    const expected = '💩�';
+
+    const actual = utf16Decode(input, false);
+
+    expect(actual).toEqual(expected);
+  });
+
+  it(`injects a replacement character when the input ends with a high surrogate`, () => {
+    // prettier-ignore
+    const input = new Uint8Array([
+      /* U+1F4A9 */ 0xd8, 0x3d, 0xdc, 0xa9,
+      /* U+1F382 */ 0xd8, 0x3c,
+    ]);
+
+    const expected = '💩�';
+
+    const actual = utf16Decode(input, false);
+
+    expect(actual).toEqual(expected);
+  });
+
+  it(`injects a replacement character when the input ends with a low surrogate`, () => {
+    // prettier-ignore
+    const input = new Uint8Array([
+      /* U+1F4A9 */ 0xd8, 0x3d, 0xdc, 0xa9,
+      /* U+1F382 */ 0xdf, 0x82,
+    ]);
+
+    const expected = '💩�';
+
+    const actual = utf16Decode(input, false);
+
+    expect(actual).toEqual(expected);
+  });
+
+  it(`injects a replacement character when low surrogates precede high surrogates`, () => {
+    // prettier-ignore
+    const input = new Uint8Array([
+      /* U+1F4A9 */ 0xd8, 0x3d, 0xdc, 0xa9,
+      /* U+1F382 */ 0xdf, 0x82, 0xd8, 0x3c,  
+      /* valid a */ 0, 97,
+    ]);
+
+    const expected = '💩�a';
+
+    const actual = utf16Decode(input, false);
+
+    expect(actual).toEqual(expected);
+  });
+
+  it(`injects a replacement character when high surrogates are not followed by low surrogates`, () => {
+    // prettier-ignore
+    const input = new Uint8Array([
+      /* valid U+1F4A9 */ 0xd8, 0x3d, 0xdc, 0xa9,
+      /* invalid U+1F382 */ 0xd8, 0x3c, 0x82, 0xdf,
+      /* valid a */ 0, 97,
+    ]);
+
+    const expected = '💩�a';
+
+    const actual = utf16Decode(input, false);
+
+    expect(actual).toEqual(expected);
+  });
+});

package/assets/pdfs/just_metadata.pdf

@@ -0,0 +1,49 @@
+%PDF-1.4
+%��??
+1 0 obj
+<<
+/Type /Catalog
+/Version /1.4
+/Pages 2 0 R
+>>
+endobj
+3 0 obj
+<<
+/Title <5469746C65206D657461646174612028537472696E67547970653D486578537472696E672C20456E636F64696E673D504446446F63456E636F64696E6729207769746820736F6D65207765697264206368617273201880A0>
+/Author <FEFF0041007500740068006F00720020006D0065007400610064006100740061002000280053007400720069006E00670054007900700065003D0048006500780053007400720069006E0067002C00200045006E0063006F00640069006E0067003D005500540046002D003100360042004500290020007700690074006800200073006F006D00650020006300680069006E00650073006500204F60600E4E486562>
+/Subject (\376\377\000\123\000\165\000\142\000\152\000\145\000\143\000\164\000\040\000\155\000\145\000\164\000\141\000\144\000\141\000\164\000\141\000\040\000\050\000\123\000\164\000\162\000\151\000\156\000\147\000\124\000\171\000\160\000\145\000\075\000\114\000\151\000\164\000\145\000\162\000\141\000\154\000\123\000\164\000\162\000\151\000\156\000\147\000\054\000\040\000\105\000\156\000\143\000\157\000\144\000\151\000\156\000\147\000\075\000\125\000\124\000\106\000\055\000\061\000\066\000\102\000\105\000\051\000\040\000\167\000\151\000\164\000\150\000\040\000\163\000\157\000\155\000\145\000\040\000\143\000\150\000\151\000\156\000\145\000\163\000\145\000\040\117\140\140\016\116\110\145\142)
+/Keywords (Keywords \155\145\164\141\144\141\164\141\040\050\123\164\162\151\156\147\124\171\160\145\075\114\151\164\145\162\141\154\123\164\162\151\156\147\054\040\105\156\143\157\144\151\156\147\075\120\104\106\104\157\143\105\156\143\157\144\151\156\147\051\040\167\151\164\150\040 some \167\145\151\162\144\040 chars \030\200\240)
+
+>>
+endobj
+2 0 obj
+<<
+/Type /Pages
+/Kids [4 0 R]
+/Count 1
+>>
+endobj
+4 0 obj
+<<
+/Type /Page
+/MediaBox [0.0 0.0 612.0 792.0]
+/Parent 2 0 R
+>>
+endobj
+xref
+0 5
+0000000000 65535 f
+0000000015 00000 n
+0000000199 00000 n
+0000000078 00000 n
+0000000256 00000 n
+trailer
+<<
+/Root 1 0 R
+/Info 3 0 R
+/ID [<9AE2C10C6CF7989704A4450D5AE54BCD> <9AE2C10C6CF7989704A4450D5AE54BCD>]
+/Size 5
+>>
+startxref
+335
+%%EOF

package/assets/pdfs/missing_endobj_keyword.pdf

@@ -0,0 +1,70 @@
+%PDF-1.3
+1 0 obj
+<</Kids  [8 0 R]
+  /Type  /Pages
+  /Count 1>>
+endobj
+2 0 obj
+<</Type  /Catalog
+  /Pages 1 0 R>>
+endobj
+3 0 obj
+<</ProcSet [/PDF /ImageC /Text]
+  /Font    <</F7 10 0 R>>>>
+endobj
+4 0 obj
+<</Type     /Info
+  /Producer (null)>>
+endobj
+5 0 obj
+<< >>
+stream
+BT
+/F7 10 Tf
+0 g
+0.0 Tc
+1 0 0 1 22.677 732.083 Tm [(Grandes) 0.0 Tc
+-250.0 (Client\350les,) 0.0 Tc
+-250.0 (Financements) 0.0 Tc
+-250.0 (et) 0.0 Tc
+-250.0 (March\351s) ] TJ
+0.0 Tc
+ET
+
+endstream
+endobj
+8 0 obj
+<</Contents  5 0 R
+  /Type      /Page
+  /Resources 3 0 R
+  /Parent    1 0 R
+  /MediaBox  [0 0 595 839]>>
+endobj
+10 0 obj
+<</Name     /F7
+  /Subtype  /Type1
+  /Type     /Font
+  /BaseFont /Times-Bold
+  /Encoding /WinAnsiEncoding>>
+xref
+0 11
+0000000000 65535 f 
+0000000009 00000 n 
+0000000070 00000 n 
+0000000120 00000 n 
+0000000195 00000 n 
+0000000249 00000 n 
+0000000000 65535 f 
+0000000000 65535 f 
+0000000470 00000 n 
+0000000000 65535 f 
+0000000590 00000 n 
+trailer
+<<
+/Size 13
+/Root 2 0 R
+/Info 4 0 R
+>>
+startxref
+707
+%%EOF

package/assets/pdfs/missing_xref_trailer_dict.pdf

@@ -0,0 +1,141 @@
+%PDF-2.0
+�̻�    
+1 0 obj
+<<
+  /Type /Catalog
+  /Pages 3 0 R
+  /Metadata 2 0 R
+>>
+endobj
+
+2 0 obj
+<<
+  /Length 2409
+  /Type /Metadata
+  /Subtype /XML
+>>
+stream
+<x:xmpmeta xmlns:x='adobe:ns:meta/' x:xmptk='Insert XMP tool name here.'>
+  <rdf:RDF xmlns:rdf='http://www.w3.org/1999/02/22-rdf-syntax-ns#'>
+    <rdf:Description rdf:about="" xmlns:pdf="http://ns.adobe.com/pdf/1.3/">
+      <pdf:Producer>Datalogics - example producer program name here</pdf:Producer>
+      <pdf:Copyright>Copyright 2017 PDF Association</pdf:Copyright>
+      <pdf:Keywords>PDF 2.0 sample example</pdf:Keywords>
+    </rdf:Description>
+    <rdf:Description rdf:about="" xmlns:xap="http://ns.adobe.com/xap/1.0/">
+      <xap:CreateDate>2017-05-24T10:30:11Z</xap:CreateDate>
+      <xap:MetadataDate>2017-07-11T07:55:11Z</xap:MetadataDate>
+      <xap:ModifyDate>2017-07-11T07:55:11Z</xap:ModifyDate>
+      <xap:CreatorTool>Datalogics - example creator tool name here</xap:CreatorTool>
+    </rdf:Description>
+    <rdf:Description rdf:about="" xmlns:dc="http://purl.org/dc/elements/1.1/">
+      <dc:format>application/pdf</dc:format>
+      <dc:title>
+        <rdf:Alt>
+          <rdf:li xml:lang="x-default">A simple PDF 2.0 example file</rdf:li>
+        </rdf:Alt>
+      </dc:title>
+      <dc:creator>
+        <rdf:Seq>
+          <rdf:li>Datalogics Incorporated</rdf:li>
+        </rdf:Seq>
+      </dc:creator>
+      <dc:description>
+        <rdf:Alt>
+          <rdf:li xml:lang="x-default">Simple PDF 2.0 file that includes commments at the top about where PDF data starts in a PDF file.</rdf:li>
+        </rdf:Alt>
+      </dc:description>
+      <dc:rights>
+        <rdf:Alt>
+          <rdf:li xml:lang="x-default">Copyright 2017 PDF Association. Licensed to the public under Creative Commons Attribution-ShareAlike 4.0 International license.</rdf:li>
+        </rdf:Alt>
+      </dc:rights>
+    </rdf:Description>
+    <rdf:Description rdf:about="" xmlns:xapRights="http://ns.adobe.com/xap/1.0/rights/">
+      <xapRights:Marked>True</xapRights:Marked>
+    </rdf:Description>
+    <rdf:Description rdf:about="" xmlns:cc="http://creativecommons.org/ns#">
+      <cc:license rdf:resource="https://creativecommons.org/licenses/sa/4.0/" />
+    </rdf:Description>
+    <rdf:Description rdf:about="" xmlns:xapMM="http://ns.adobe.com/xap/1.0/mm/">
+      <xapMM:DocumentID>uuid:2295ab33-7b2c-4faa-3741-923458bccfbf</xapMM:DocumentID>
+      <xapMM:InstanceID>uuid:81bee377-edd0-46aa-9238-6bb4dd921218</xapMM:InstanceID>
+    </rdf:Description>
+  </rdf:RDF>
+</x:xmpmeta>
+endstream
+endobj
+ 
+3 0 obj
+<<
+  /Type /Pages
+  /Kids [4 0 R]
+  /Count 1
+>>
+endobj
+
+4 0 obj
+<<
+  /Type /Page
+  /Parent 3 0 R
+  /MediaBox [0 0 612 396]
+  /Contents [6 0 R]
+  /Resources <<
+    /Font << /F1 7 0 R >>
+  >>
+>>
+endobj
+
+6 0 obj
+<< /Length 68  >>
+stream
+BT
+  /F1 24 Tf
+  100 100 Td
+  (This is a PDF 2.0 document) Tj
+ET
+endstream
+endobj
+
+% Font notes for PDF 2.0:
+% 1) The Name entry is deprecated in PDF 2.0
+% 2) All fonts, even the standard 14 fonts, are now required to have
+%   FirstChar, LastChar, Widths and a FontDescriptor
+7 0 obj
+<<
+  /Type /Font
+  /Subtype /Type1
+  /BaseFont /Helvetica
+  /FirstChar 33
+  /LastChar 126
+  /Widths 8 0 R
+  /FontDescriptor 9 0 R
+>>
+endobj
+
+8 0 obj
+[ 278 355 556 556 889 667 222 333 333 389 584 278 333 278 278 556
+  556 556 556 556 556 556 556 556 556 278 278 584 584 584 556 1015
+  667 667 722 722 667 611 778 722 278 500 667 556 833 722 778 667
+  778 722 667 611 722 667 944 667 667 611 278 278 278 469 556 222
+  556 556 500 556 556 278 556 556 222 222 500 222 833 556 556 556
+  556 333 500 278 556 500 722 500 500 500 334 260 334 584 ]
+endobj
+
+% This FontDescriptor contains only the required entries for PDF 2.0
+% for unembedded standard 14 fonts that contain Latin characters
+9 0 obj
+<<
+  /Type /FontDescriptor
+  /FontName /Helvetica
+  /Flags 32
+  /FontBBox [ -166 -225 1000 931 ]
+  /ItalicAngle 0
+  /Ascent 718
+  /Descent -207
+  /CapHeight 718
+  /StemV 88
+  /MissingWidth 278
+>>
+endobj
+