html2doc 1.0.4 → 1.1.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (18) hide show
  1. checksums.yaml +4 -4
  2. data/.github/workflows/rake.yml +42 -0
  3. data/.gitignore +2 -0
  4. data/.rubocop.yml +6 -2
  5. data/README.adoc +1 -3
  6. data/html2doc.gemspec +4 -3
  7. data/lib/html2doc/base.rb +15 -6
  8. data/lib/html2doc/math.rb +86 -6
  9. data/lib/html2doc/mime.rb +19 -10
  10. data/lib/html2doc/mml2omml.xsl +35 -7
  11. data/lib/html2doc/version.rb +1 -1
  12. data/spec/html2doc_spec.rb +63 -21
  13. metadata +26 -16
  14. data/.github/workflows/macos.yml +0 -38
  15. data/.github/workflows/ubuntu.yml +0 -56
  16. data/.github/workflows/windows.yml +0 -40
  17. data/.rubocop.ribose.yml +0 -65
  18. data/.rubocop.tb.yml +0 -650
data/lib/html2doc/version.rb CHANGED
@@ -1,3 +1,3 @@
1
1
  module Html2Doc
2
- VERSION = "1.0.4".freeze
2
+ VERSION = "1.1.0".freeze
3
3
  end
data/spec/html2doc_spec.rb CHANGED
@@ -36,7 +36,8 @@ MIME-Version: 1.0
36
36
  Content-Type: multipart/related; boundary="----=_NextPart_"
37
37
 
38
38
  ------=_NextPart_
39
- Content-Location: file:///C:/Doc/test.htm
39
+ Content-ID: <test.htm>
40
+ Content-Disposition: inline; filename="test.htm"
40
41
  Content-Type: text/html; charset="utf-8"
41
42
 
42
43
  <?xml version="1.0"?>
@@ -51,7 +52,7 @@ Content-Type: text/html; charset="utf-8"
51
52
  <![endif]-->
52
53
  <meta http-equiv=Content-Type content="text/html; charset=utf-8"/>
53
54
 
54
- <link rel=File-List href="test_files/filelist.xml"/>
55
+ <link rel=File-List href="cid:filelist.xml"/>
55
56
  <title>blank</title><style><![CDATA[
56
57
  <!--
57
58
  HDR
@@ -73,7 +74,8 @@ end
73
74
 
74
75
  WORD_FTR1 = <<~FTR
75
76
  ------=_NextPart_
76
- Content-Location: file:///C:/Doc/test_files/filelist.xml
77
+ Content-ID: <filelist.xml>
78
+ Content-Disposition: inline; filename="filelist.xml"
77
79
  Content-Transfer-Encoding: base64
78
80
  Content-Type: #{Html2Doc::mime_type('filelist.xml')}
79
81
 
@@ -86,7 +88,8 @@ FTR
86
88
 
87
89
  WORD_FTR2 = <<~FTR
88
90
  ------=_NextPart_
89
- Content-Location: file:///C:/Doc/test_files/filelist.xml
91
+ Content-ID: <filelist.xml>
92
+ Content-Disposition: inline; filename="filelist.xml"
90
93
  Content-Transfer-Encoding: base64
91
94
  Content-Type: #{Html2Doc::mime_type('filelist.xml')}
92
95
  PHhtbCB4bWxuczpvPSJ1cm46c2NoZW1hcy1taWNyb3NvZnQtY29tOm9mZmljZTpvZmZpY2UiPgog
@@ -97,7 +100,8 @@ FTR
97
100
 
98
101
  WORD_FTR3 = <<~FTR
99
102
  ------=_NextPart_
100
- Content-Location: file:///C:/Doc/test_files/filelist.xml
103
+ Content-ID: <filelist.xml>
104
+ Content-Disposition: inline; filename="filelist.xml"
101
105
  Content-Transfer-Encoding: base64
102
106
  Content-Type: #{Html2Doc::mime_type('filelist.xml')}
103
107
 
@@ -106,7 +110,8 @@ ICAgICAgIDxvOk1haW5GaWxlIEhSZWY9Ii4uL3Rlc3QuaHRtIi8+ICA8bzpGaWxlIEhSZWY9IjFh
106
110
  YzIwNjVmLTAzZjAtNGM3YS1iOWE2LTkyZTgyMDU5MWJmMC5wbmciLz4KICA8bzpGaWxlIEhSZWY9
107
111
  ImZpbGVsaXN0LnhtbCIvPgo8L3htbD4K
108
112
  ------=_NextPart_
109
- Content-Location: file:///C:/Doc/test_files/cb7b0d19-891e-4634-815a-570d019d454c.png
113
+ Content-ID: <cb7b0d19-891e-4634-815a-570d019d454c.png>
114
+ Content-Disposition: inline; filename="cb7b0d19-891e-4634-815a-570d019d454c.png"
110
115
  Content-Transfer-Encoding: base64
111
116
  Content-Type: image/png
112
117
  ------=_NextPart_--
@@ -329,9 +334,9 @@ RSpec.describe Html2Doc do
329
334
  expect(HTMLEntities.new.encode(hdr, :hexadecimal).
330
335
  gsub(/\&#x3c;/, "<").gsub(/\&#x3e;/, ">").gsub(/\&#x27;/, "'").gsub(/\&#x22;/, '"').
331
336
  gsub(/\&#xd;/, "&#xa;").gsub(/\&#xa;/, "\n")).to match_fuzzy(HEADERHTML)
332
- expect(html.sub(%r{Content-Location: file:///C:/Doc/test_files/header.html.*$}m, "")).
337
+ expect(html.sub(%r{Content-ID: <header.html>.*$}m, "")).
333
338
  to match_fuzzy(<<~OUTPUT)
334
- #{WORD_HDR} #{DEFAULT_STYLESHEET.gsub(/FILENAME/, "test")}
339
+ #{WORD_HDR} #{DEFAULT_STYLESHEET.gsub(/url\("[^"]+"\)/, "url(cid:header.html)")}
335
340
  #{WORD_HDR_END} #{word_body("", '<div style="mso-element:footnote-list"/>')} #{WORD_FTR2}
336
341
  OUTPUT
337
342
  end
@@ -340,7 +345,7 @@ RSpec.describe Html2Doc do
340
345
  Html2Doc.process(html_input(""), filename: "test", header_file: "spec/header_img.html")
341
346
  doc = guid_clean(File.read("test.doc", encoding: "utf-8"))
342
347
  expect(doc).to match(%r{Content-Type: image/png})
343
- expect(doc).to match(%r{file:///C:/Doc/test_files/[^.]+\.png})
348
+ expect(doc).to match(%r{iVBORw0KGgoAAAANSUhEUgAAA5cAAAN7CAYAAADRE24cAAAgAElEQVR4XuydB5gUxdaGC65gTogB})
344
349
  end
345
350
 
346
351
  it "processes a header with an image with absolute path" do
@@ -351,7 +356,7 @@ RSpec.describe Html2Doc do
351
356
  Html2Doc.process(html_input(""), filename: "test", header_file: "spec/header_img1.html")
352
357
  doc = guid_clean(File.read("test.doc", encoding: "utf-8"))
353
358
  expect(doc).to match(%r{Content-Type: image/png})
354
- expect(doc).to match(%r{file:///C:/Doc/test_files/[^.]+\.png})
359
+ expect(doc).to match(%r{iVBORw0KGgoAAAANSUhEUgAAA5cAAAN7CAYAAADRE24cAAAgAElEQVR4XuydB5gUxdaGC65gTogB})
355
360
  end
356
361
 
357
362
 
@@ -374,7 +379,21 @@ RSpec.describe Html2Doc do
374
379
  #{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
375
380
  #{word_body(%{
376
381
  <div><m:oMath>
377
- <m:nary><m:naryPr><m:chr m:val="&#x2211;"></m:chr><m:limLoc m:val="undOvr"></m:limLoc><m:grow m:val="on"></m:grow><m:subHide m:val="off"></m:subHide><m:supHide m:val="off"></m:supHide></m:naryPr><m:sub><m:r><m:t>i=1</m:t></m:r></m:sub><m:sup><m:r><m:t>n</m:t></m:r></m:sup><m:e><m:sSup><m:e><m:r><m:t>i</m:t></m:r></m:e><m:sup><m:r><m:t>3</m:t></m:r></m:sup></m:sSup></m:e></m:nary><m:r><m:t>=</m:t></m:r><m:sSup><m:e><m:d><m:dPr><m:sepChr m:val=","></m:sepChr></m:dPr><m:e><m:f><m:fPr><m:type m:val="bar"></m:type></m:fPr><m:num><m:r><m:t>n</m:t></m:r><m:d><m:dPr><m:sepChr m:val=","></m:sepChr></m:dPr><m:e><m:r><m:t>n+1</m:t></m:r></m:e></m:d></m:num><m:den><m:r><m:t>2</m:t></m:r></m:den></m:f></m:e></m:d></m:e><m:sup><m:r><m:t>2</m:t></m:r></m:sup></m:sSup><m:r><m:rPr><m:nor></m:nor></m:rPr><m:t>"integer"</m:t></m:r><m:r><m:t>)</m:t></m:r>
382
+ <m:nary><m:naryPr><m:chr m:val="&#x2211;"></m:chr><m:limLoc m:val="undOvr"></m:limLoc><m:grow m:val="on"></m:grow><m:subHide m:val="off"></m:subHide><m:supHide m:val="off"></m:supHide></m:naryPr><m:sub><m:r><m:t>i=1</m:t></m:r></m:sub><m:sup><m:r><m:t>n</m:t></m:r></m:sup><m:e><m:sSup><m:e><m:r><m:t>i</m:t></m:r></m:e><m:sup><m:r><m:t>3</m:t></m:r></m:sup></m:sSup></m:e></m:nary><span style="font-style:normal;"><m:r><m:rPr><m:sty m:val="p"></m:sty></m:rPr><m:t>=</m:t></m:r></span><m:sSup><m:e><m:d><m:dPr><m:sepChr m:val=","></m:sepChr></m:dPr><m:e><m:f><m:fPr><m:type m:val="bar"></m:type></m:fPr><m:num><m:r><m:t>n</m:t></m:r><m:d><m:dPr><m:sepChr m:val=","></m:sepChr></m:dPr><m:e><m:r><m:t>n+1</m:t></m:r></m:e></m:d></m:num><m:den><m:r><m:t>2</m:t></m:r></m:den></m:f></m:e></m:d></m:e><m:sup><m:r><m:t>2</m:t></m:r></m:sup></m:sSup><m:r><m:rPr><m:nor></m:nor></m:rPr><m:t>"integer"</m:t></m:r><span style="font-style:normal;"><m:r><m:rPr><m:sty m:val="p"></m:sty></m:rPr><m:t>)</m:t></m:r></span>
383
+ </m:oMath>
384
+ </div>}, '<div style="mso-element:footnote-list"/>')}
385
+ #{WORD_FTR1}
386
+ OUTPUT
387
+ end
388
+
389
+ it "processes mstyle" do
390
+ Html2Doc.process(html_input(%[<div>{{bb (-log_2 (p_u)) bb "BB" bbb "BBB" cc "CC" bcc "BCC" tt "TT" fr "FR" bfr "BFR" sf "SF" bsf "BSFα" sfi "SFI" sfbi "SFBIα" bii "BII" ii "II"}}</div>]), filename: "test", asciimathdelims: ["{{", "}}"])
391
+ expect(guid_clean(File.read("test.doc", encoding: "utf-8"))).
392
+ to match_fuzzy(<<~OUTPUT)
393
+ #{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
394
+ #{word_body(%{
395
+ <div><m:oMath>
396
+ <span style="font-style:normal;font-weight:bold;"><m:r><m:rPr><m:sty m:val="b"></m:sty></m:rPr><m:t>&#x2212;</m:t></m:r></span><m:sSub><m:e><span style="font-style:normal;font-weight:bold;"><m:r><m:rPr><m:sty m:val="b"></m:sty></m:rPr><m:t>log</m:t></m:r></span></m:e><m:sub><span style="font-style:normal;font-weight:bold;"><m:r><m:rPr><m:sty m:val="b"></m:sty></m:rPr><m:t>2</m:t></m:r></span></m:sub></m:sSub><m:d><m:dPr><m:sepChr m:val=","></m:sepChr></m:dPr><m:e><m:sSub><m:e><span style="font-style:normal;font-weight:bold;"><m:r><m:rPr><m:sty m:val="b"></m:sty></m:rPr><m:t>p</m:t></m:r></span></m:e><m:sub><span style="font-style:normal;font-weight:bold;"><m:r><m:rPr><m:sty m:val="b"></m:sty></m:rPr><m:t>u</m:t></m:r></span></m:sub></m:sSub></m:e></m:d><span style="font-style:normal;font-weight:bold;"><m:r><m:rPr><m:nor></m:nor><m:sty m:val="b"></m:sty></m:rPr><m:t>BB</m:t></m:r></span><m:r><m:rPr><m:nor></m:nor><m:scr m:val="double-struck"></m:scr><m:sty m:val="p"></m:sty></m:rPr><m:t>&#x1D539;&#x1D539;&#x1D539;</m:t></m:r><m:r><m:rPr><m:nor></m:nor><m:scr m:val="script"></m:scr></m:rPr><m:t>&#x1D49E;&#x1D49E;</m:t></m:r><m:r><m:rPr><m:nor></m:nor><m:scr m:val="script"></m:scr><m:sty m:val="b"></m:sty></m:rPr><m:t>&#x1D4D1;&#x1D4D2;&#x1D4D2;</m:t></m:r><m:r><m:rPr><m:nor></m:nor><m:scr m:val="monospace"></m:scr><m:sty m:val="p"></m:sty></m:rPr><m:t>&#x1D683;&#x1D683;</m:t></m:r><m:r><m:rPr><m:nor></m:nor><m:scr m:val="fraktur"></m:scr><m:sty m:val="p"></m:sty></m:rPr><m:t>&#x1D509;&#x211C;</m:t></m:r><m:r><m:rPr><m:nor></m:nor><m:scr m:val="fraktur"></m:scr><m:sty m:val="b"></m:sty></m:rPr><m:t>&#x1D56D;&#x1D571;&#x1D57D;</m:t></m:r><m:r><m:rPr><m:nor></m:nor><m:scr m:val="sans-serif"></m:scr><m:sty m:val="p"></m:sty></m:rPr><m:t>&#x1D5B2;&#x1D5A5;</m:t></m:r><m:r><m:rPr><m:nor></m:nor><m:scr m:val="sans-serif"></m:scr><m:sty m:val="b"></m:sty></m:rPr><m:t>&#x1D5D5;&#x1D5E6;&#x1D5D9;&#x1D770;</m:t></m:r><m:r><m:rPr><m:nor></m:nor><m:scr m:val="sans-serif"></m:scr></m:rPr><m:t>&#x1D5B2;&#x1D5A5;&#x1D5A8;</m:t></m:r><m:r><m:rPr><m:nor></m:nor><m:scr m:val="sans-serif"></m:scr><m:sty m:val="bi"></m:sty></m:rPr><m:t>&#x1D64E;&#x1D641;&#x1D63D;&#x1D644;&#x1D7AA;</m:t></m:r><span class="nostem" style="font-weight:bold;"><em></em><m:r><m:rPr><m:nor></m:nor><m:sty m:val="bi"></m:sty></m:rPr><m:t>BII</m:t></m:r></span><span class="nostem"><em></em><m:r><m:rPr><m:nor></m:nor><m:sty m:val="i"></m:sty></m:rPr><m:t>II</m:t></m:r></span>
378
397
  </m:oMath>
379
398
  </div>}, '<div style="mso-element:footnote-list"/>')}
380
399
  #{WORD_FTR1}
@@ -386,11 +405,11 @@ RSpec.describe Html2Doc do
386
405
  expect(guid_clean(File.read("test.doc", encoding: "utf-8"))).
387
406
  to match_fuzzy(<<~OUTPUT)
388
407
  #{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
389
- #{word_body("
408
+ #{word_body('
390
409
  <div><m:oMath>
391
- <m:r><m:t>text</m:t></m:r><m:r><m:rPr><m:nor></m:nor></m:rPr><m:t>&#xA0;integer&#xA0;</m:t></m:r><m:r><m:t>)</m:t></m:r>
410
+ <m:r><m:t>text</m:t></m:r><m:r><m:rPr><m:nor></m:nor></m:rPr><m:t>&#xA0;integer&#xA0;</m:t></m:r><span style="font-style:normal;"><m:r><m:rPr><m:sty m:val="p"></m:sty></m:rPr><m:t>)</m:t></m:r></span>
392
411
  </m:oMath>
393
- </div>", '<div style="mso-element:footnote-list"/>')}
412
+ </div>', '<div style="mso-element:footnote-list"/>')}
394
413
  #{WORD_FTR1}
395
414
  OUTPUT
396
415
  end
@@ -410,6 +429,21 @@ RSpec.describe Html2Doc do
410
429
  OUTPUT
411
430
  end
412
431
 
432
+ it "unwraps accent in MathML" do
433
+ Html2Doc.process(html_input("<div><math xmlns='http://www.w3.org/1998/Math/MathML'>
434
+ <mover accent='true'><mrow><mi>p</mi></mrow><mrow><mo>^</mo></mrow></mover>
435
+ </math></div>"), filename: "test", asciimathdelims: ["{{", "}}"])
436
+ expect(guid_clean(File.read("test.doc", encoding: "utf-8"))).
437
+ to match_fuzzy(<<~OUTPUT)
438
+ #{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
439
+ #{word_body('<div><m:oMath>
440
+ <m:acc><m:accPr><m:chr m:val="^"></m:chr></m:accPr><m:e><m:r><m:t>p</m:t></m:r></m:e></m:acc>
441
+ </m:oMath>
442
+ </div>', '<div style="mso-element:footnote-list"/>')}
443
+ #{WORD_FTR1}
444
+ OUTPUT
445
+ end
446
+
413
447
  it "left-aligns AsciiMath" do
414
448
  Html2Doc.process(html_input("<div style='text-align:left;'>{{sum_(i=1)^n i^3=((n(n+1))/2)^2}}</div>"), filename: "test", asciimathdelims: ["{{", "}}"])
415
449
  expect(guid_clean(File.read("test.doc", encoding: "utf-8"))).
@@ -417,7 +451,7 @@ RSpec.describe Html2Doc do
417
451
  #{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
418
452
  #{word_body(%{
419
453
  <div style="text-align:left;"><m:oMathPara><m:oMathParaPr><m:jc m:val="left"/></m:oMathParaPr><m:oMath>
420
- <m:nary><m:naryPr><m:chr m:val="&#x2211;"></m:chr><m:limLoc m:val="undOvr"></m:limLoc><m:grow m:val="on"></m:grow><m:subHide m:val="off"></m:subHide><m:supHide m:val="off"></m:supHide></m:naryPr><m:sub><m:r><m:t>i=1</m:t></m:r></m:sub><m:sup><m:r><m:t>n</m:t></m:r></m:sup><m:e><m:sSup><m:e><m:r><m:t>i</m:t></m:r></m:e><m:sup><m:r><m:t>3</m:t></m:r></m:sup></m:sSup></m:e></m:nary><m:r><m:t>=</m:t></m:r><m:sSup><m:e><m:d><m:dPr><m:sepChr m:val=","></m:sepChr></m:dPr><m:e><m:f><m:fPr><m:type m:val="bar"></m:type></m:fPr><m:num><m:r><m:t>n</m:t></m:r><m:d><m:dPr><m:sepChr m:val=","></m:sepChr></m:dPr><m:e><m:r><m:t>n+1</m:t></m:r></m:e></m:d></m:num><m:den><m:r><m:t>2</m:t></m:r></m:den></m:f></m:e></m:d></m:e><m:sup><m:r><m:t>2</m:t></m:r></m:sup></m:sSup>
454
+ <m:nary><m:naryPr><m:chr m:val="&#x2211;"></m:chr><m:limLoc m:val="undOvr"></m:limLoc><m:grow m:val="on"></m:grow><m:subHide m:val="off"></m:subHide><m:supHide m:val="off"></m:supHide></m:naryPr><m:sub><m:r><m:t>i=1</m:t></m:r></m:sub><m:sup><m:r><m:t>n</m:t></m:r></m:sup><m:e><m:sSup><m:e><m:r><m:t>i</m:t></m:r></m:e><m:sup><m:r><m:t>3</m:t></m:r></m:sup></m:sSup></m:e></m:nary><span style="font-style:normal;"><m:r><m:rPr><m:sty m:val="p"></m:sty></m:rPr><m:t>=</m:t></m:r></span><m:sSup><m:e><m:d><m:dPr><m:sepChr m:val=","></m:sepChr></m:dPr><m:e><m:f><m:fPr><m:type m:val="bar"></m:type></m:fPr><m:num><m:r><m:t>n</m:t></m:r><m:d><m:dPr><m:sepChr m:val=","></m:sepChr></m:dPr><m:e><m:r><m:t>n+1</m:t></m:r></m:e></m:d></m:num><m:den><m:r><m:t>2</m:t></m:r></m:den></m:f></m:e></m:d></m:e><m:sup><m:r><m:t>2</m:t></m:r></m:sup></m:sSup>
421
455
  </m:oMath>
422
456
  </m:oMathPara></div>}, '<div style="mso-element:footnote-list"/>')}
423
457
  #{WORD_FTR1}
@@ -431,13 +465,21 @@ RSpec.describe Html2Doc do
431
465
  #{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
432
466
  #{word_body(%{
433
467
  <div style="text-align:right;"><m:oMathPara><m:oMathParaPr><m:jc m:val="right"/></m:oMathParaPr><m:oMath>
434
- <m:nary><m:naryPr><m:chr m:val="&#x2211;"></m:chr><m:limLoc m:val="undOvr"></m:limLoc><m:grow m:val="on"></m:grow><m:subHide m:val="off"></m:subHide><m:supHide m:val="off"></m:supHide></m:naryPr><m:sub><m:r><m:t>i=1</m:t></m:r></m:sub><m:sup><m:r><m:t>n</m:t></m:r></m:sup><m:e><m:sSup><m:e><m:r><m:t>i</m:t></m:r></m:e><m:sup><m:r><m:t>3</m:t></m:r></m:sup></m:sSup></m:e></m:nary><m:r><m:t>=</m:t></m:r><m:sSup><m:e><m:d><m:dPr><m:sepChr m:val=","></m:sepChr></m:dPr><m:e><m:f><m:fPr><m:type m:val="bar"></m:type></m:fPr><m:num><m:r><m:t>n</m:t></m:r><m:d><m:dPr><m:sepChr m:val=","></m:sepChr></m:dPr><m:e><m:r><m:t>n+1</m:t></m:r></m:e></m:d></m:num><m:den><m:r><m:t>2</m:t></m:r></m:den></m:f></m:e></m:d></m:e><m:sup><m:r><m:t>2</m:t></m:r></m:sup></m:sSup>
468
+ <m:nary><m:naryPr><m:chr m:val="&#x2211;"></m:chr><m:limLoc m:val="undOvr"></m:limLoc><m:grow m:val="on"></m:grow><m:subHide m:val="off"></m:subHide><m:supHide m:val="off"></m:supHide></m:naryPr><m:sub><m:r><m:t>i=1</m:t></m:r></m:sub><m:sup><m:r><m:t>n</m:t></m:r></m:sup><m:e><m:sSup><m:e><m:r><m:t>i</m:t></m:r></m:e><m:sup><m:r><m:t>3</m:t></m:r></m:sup></m:sSup></m:e></m:nary><span style="font-style:normal;"><m:r><m:rPr><m:sty m:val="p"></m:sty></m:rPr><m:t>=</m:t></m:r></span><m:sSup><m:e><m:d><m:dPr><m:sepChr m:val=","></m:sepChr></m:dPr><m:e><m:f><m:fPr><m:type m:val="bar"></m:type></m:fPr><m:num><m:r><m:t>n</m:t></m:r><m:d><m:dPr><m:sepChr m:val=","></m:sepChr></m:dPr><m:e><m:r><m:t>n+1</m:t></m:r></m:e></m:d></m:num><m:den><m:r><m:t>2</m:t></m:r></m:den></m:f></m:e></m:d></m:e><m:sup><m:r><m:t>2</m:t></m:r></m:sup></m:sSup>
435
469
  </m:oMath>
436
470
  </m:oMathPara></div>}, '<div style="mso-element:footnote-list"/>')}
437
471
  #{WORD_FTR1}
438
472
  OUTPUT
439
473
  end
440
474
 
475
+ it "raises error in processing of broken AsciiMath" do
476
+ begin
477
+ expect{ Html2Doc.process(html_input(%[<div style='text-align:right;'>{{u_c = 6.6"unitsml(kHz)}}</div>]), filename: "test", asciimathdelims: ["{{", "}}"]) }.to output('parsing: u_c = 6.6"unitsml(kHz)').to_stderr
478
+ rescue StandardError
479
+ end
480
+ expect{ Html2Doc.process(html_input(%[<div style='text-align:right;'>{{u_c = 6.6"unitsml(kHz)}}</div>]), filename: "test", asciimathdelims: ["{{", "}}"]) }.to raise_error(StandardError)
481
+ end
482
+
441
483
  it "wraps msup after munderover in MathML" do
442
484
  Html2Doc.process(html_input("<div><math xmlns='http://www.w3.org/1998/Math/MathML'>
443
485
  <munderover><mo>&#x2211;</mo><mrow><mi>i</mi><mo>=</mo><mn>0</mn></mrow><mrow><mi>n</mi></mrow></munderover><msup><mn>2</mn><mrow><mi>i</mi></mrow></msup></math></div>"), filename: "test", asciimathdelims: ["{{", "}}"])
@@ -498,7 +540,7 @@ RSpec.describe Html2Doc do
498
540
  expect(testdoc).to match(%r{Content-Type: image/png})
499
541
  expect(image_clean(guid_clean(testdoc))).to match_fuzzy(<<~OUTPUT)
500
542
  #{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
501
- #{image_clean(word_body('<img src="test_files/cb7b0d19-891e-4634-815a-570d019d454c.png" width="400" height="388"></img>', '<div style="mso-element:footnote-list"/>'))}
543
+ #{image_clean(word_body('<img src="cid:cb7b0d19-891e-4634-815a-570d019d454c.png" width="400" height="388"></img>', '<div style="mso-element:footnote-list"/>'))}
502
544
  #{image_clean(WORD_FTR3)}
503
545
  OUTPUT
504
546
  end
@@ -510,7 +552,7 @@ RSpec.describe Html2Doc do
510
552
  expect(testdoc).to match(%r{Content-Type: image/gif})
511
553
  expect(image_clean(guid_clean(testdoc))).to match_fuzzy(<<~OUTPUT)
512
554
  #{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
513
- #{image_clean(word_body('<img src="test_files/cb7b0d19-891e-4634-815a-570d019d454c.gif" width="400" height="118"></img>', '<div style="mso-element:footnote-list"/>'))}
555
+ #{image_clean(word_body('<img src="cid:cb7b0d19-891e-4634-815a-570d019d454c.gif" width="400" height="118"></img>', '<div style="mso-element:footnote-list"/>'))}
514
556
  #{image_clean(WORD_FTR3).gsub(/image\.png/, "image.gif")}
515
557
  OUTPUT
516
558
  end
@@ -522,7 +564,7 @@ RSpec.describe Html2Doc do
522
564
  expect(testdoc).to match(%r{Content-Type: image/jpeg})
523
565
  expect(image_clean(guid_clean(testdoc))).to match_fuzzy(<<~OUTPUT)
524
566
  #{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
525
- #{image_clean(word_body('<img src="test_files/cb7b0d19-891e-4634-815a-570d019d454c.jpg" width="208" height="680"></img>', '<div style="mso-element:footnote-list"/>'))}
567
+ #{image_clean(word_body('<img src="cid:cb7b0d19-891e-4634-815a-570d019d454c.jpg" width="208" height="680"></img>', '<div style="mso-element:footnote-list"/>'))}
526
568
  #{image_clean(WORD_FTR3).gsub(/image\.png/, "image.jpg")}
527
569
  OUTPUT
528
570
  end
@@ -576,7 +618,7 @@ RSpec.describe Html2Doc do
576
618
  expect(testdoc).to match(%r{Content-Type: image/png})
577
619
  expect(image_clean(guid_clean(testdoc))).to match_fuzzy(<<~OUTPUT)
578
620
  #{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
579
- #{image_clean(word_body('<img src="test_files/cb7b0d19-891e-4634-815a-570d019d454c.png" width="400" height="388"></img>', '<div style="mso-element:footnote-list"/>'))}
621
+ #{image_clean(word_body('<img src="cid:cb7b0d19-891e-4634-815a-570d019d454c.png" width="400" height="388"></img>', '<div style="mso-element:footnote-list"/>'))}
580
622
  #{image_clean(WORD_FTR3)}
581
623
  OUTPUT
582
624
  end
@@ -753,7 +795,7 @@ RSpec.describe Html2Doc do
753
795
  Html2Doc.process(html_input(simple_body), filename: "spec/test", debug: true)
754
796
  testdoc = File.read("spec/test.doc", encoding: "utf-8")
755
797
  base64_image = testdoc[/image\/png\n\n(.*?)\n\n----/m, 1].gsub!("\n", "")
756
- base64_image_basename = testdoc[%r{Content-Location: file:///C:/Doc/test_files/([0-9a-z\-]+)\.png}m, 1]
798
+ base64_image_basename = testdoc[%r{Content-ID: <([0-9a-z\-]+)\.png}m, 1]
757
799
  doc_bin_image = Base64.strict_decode64(base64_image)
758
800
  file_bin_image = IO.read("spec/test_files/#{base64_image_basename}.png", mode: "rb")
759
801
  expect(doc_bin_image).to eq file_bin_image
metadata CHANGED
@@ -1,14 +1,14 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: html2doc
3
3
  version: !ruby/object:Gem::Version
4
- version: 1.0.4
4
+ version: 1.1.0
5
5
  platform: ruby
6
6
  authors:
7
7
  - Ribose Inc.
8
8
  autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2020-08-27 00:00:00.000000000 Z
11
+ date: 2021-03-30 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: htmlentities
@@ -56,14 +56,14 @@ dependencies:
56
56
  name: nokogiri
57
57
  requirement: !ruby/object:Gem::Requirement
58
58
  requirements:
59
- - - ">="
59
+ - - "~>"
60
60
  - !ruby/object:Gem::Version
61
61
  version: 1.10.4
62
62
  type: :runtime
63
63
  prerelease: false
64
64
  version_requirements: !ruby/object:Gem::Requirement
65
65
  requirements:
66
- - - ">="
66
+ - - "~>"
67
67
  - !ruby/object:Gem::Version
68
68
  version: 1.10.4
69
69
  - !ruby/object:Gem::Dependency
@@ -100,14 +100,28 @@ dependencies:
100
100
  requirements:
101
101
  - - "~>"
102
102
  - !ruby/object:Gem::Version
103
- version: 2.0.0
103
+ version: 2.0.2
104
104
  type: :runtime
105
105
  prerelease: false
106
106
  version_requirements: !ruby/object:Gem::Requirement
107
107
  requirements:
108
108
  - - "~>"
109
109
  - !ruby/object:Gem::Version
110
- version: 2.0.0
110
+ version: 2.0.2
111
+ - !ruby/object:Gem::Dependency
112
+ name: plane1converter
113
+ requirement: !ruby/object:Gem::Requirement
114
+ requirements:
115
+ - - "~>"
116
+ - !ruby/object:Gem::Version
117
+ version: 0.0.1
118
+ type: :runtime
119
+ prerelease: false
120
+ version_requirements: !ruby/object:Gem::Requirement
121
+ requirements:
122
+ - - "~>"
123
+ - !ruby/object:Gem::Version
124
+ version: 0.0.1
111
125
  - !ruby/object:Gem::Dependency
112
126
  name: byebug
113
127
  requirement: !ruby/object:Gem::Requirement
@@ -196,16 +210,16 @@ dependencies:
196
210
  name: rubocop
197
211
  requirement: !ruby/object:Gem::Requirement
198
212
  requirements:
199
- - - '='
213
+ - - "~>"
200
214
  - !ruby/object:Gem::Version
201
- version: 0.54.0
215
+ version: 1.5.2
202
216
  type: :development
203
217
  prerelease: false
204
218
  version_requirements: !ruby/object:Gem::Requirement
205
219
  requirements:
206
- - - '='
220
+ - - "~>"
207
221
  - !ruby/object:Gem::Version
208
- version: 0.54.0
222
+ version: 1.5.2
209
223
  - !ruby/object:Gem::Dependency
210
224
  name: simplecov
211
225
  requirement: !ruby/object:Gem::Requirement
@@ -259,15 +273,11 @@ extensions: []
259
273
  extra_rdoc_files: []
260
274
  files:
261
275
  - ".gitattributes"
262
- - ".github/workflows/macos.yml"
263
- - ".github/workflows/ubuntu.yml"
264
- - ".github/workflows/windows.yml"
276
+ - ".github/workflows/rake.yml"
265
277
  - ".gitignore"
266
278
  - ".hound.yml"
267
279
  - ".oss-guides.rubocop.yml"
268
280
  - ".rspec"
269
- - ".rubocop.ribose.yml"
270
- - ".rubocop.tb.yml"
271
281
  - ".rubocop.yml"
272
282
  - CODE_OF_CONDUCT.md
273
283
  - Gemfile
@@ -324,7 +334,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
324
334
  - !ruby/object:Gem::Version
325
335
  version: '0'
326
336
  requirements: []
327
- rubygems_version: 3.0.3
337
+ rubygems_version: 3.1.4
328
338
  signing_key:
329
339
  specification_version: 4
330
340
  summary: Convert HTML document to Microsoft Word document
data/.github/workflows/macos.yml DELETED
@@ -1,38 +0,0 @@
1
- # Auto-generated by Cimas: Do not edit it manually!
2
- # See https://github.com/metanorma/cimas
3
- name: macos
4
-
5
- on:
6
- push:
7
- branches: [ master ]
8
- pull_request:
9
- paths-ignore:
10
- - .github/workflows/ubuntu.yml
11
- - .github/workflows/windows.yml
12
-
13
- jobs:
14
- test-macos:
15
- name: Test on Ruby ${{ matrix.ruby }} macOS
16
- runs-on: macos-latest
17
- continue-on-error: ${{ matrix.experimental }}
18
- strategy:
19
- fail-fast: false
20
- matrix:
21
- ruby: [ '2.6', '2.5', '2.4' ]
22
- experimental: [false]
23
- include:
24
- - ruby: '2.7'
25
- experimental: true
26
- steps:
27
- - uses: actions/checkout@master
28
- - name: Use Ruby
29
- uses: actions/setup-ruby@v1
30
- with:
31
- ruby-version: ${{ matrix.ruby }}
32
- - name: Update gems
33
- run: |
34
- sudo gem install bundler --force
35
- bundle install --jobs 4 --retry 3
36
- - name: Run specs
37
- run: |
38
- bundle exec rake
data/.github/workflows/ubuntu.yml DELETED
@@ -1,56 +0,0 @@
1
- # Auto-generated by Cimas: Do not edit it manually!
2
- # See https://github.com/metanorma/cimas
3
- name: ubuntu
4
-
5
- on:
6
- push:
7
- branches: [ master ]
8
- tags:
9
- - '*'
10
- pull_request:
11
- paths-ignore:
12
- - .github/workflows/macos.yml
13
- - .github/workflows/windows.yml
14
-
15
- jobs:
16
- test-linux:
17
- name: Test on Ruby ${{ matrix.ruby }} Ubuntu
18
- runs-on: ubuntu-latest
19
- continue-on-error: ${{ matrix.experimental }}
20
- strategy:
21
- fail-fast: false
22
- matrix:
23
- ruby: [ '2.6', '2.5', '2.4' ]
24
- experimental: [false]
25
- include:
26
- - ruby: '2.7'
27
- experimental: true
28
- steps:
29
- - uses: actions/checkout@master
30
- - name: Use Ruby
31
- uses: actions/setup-ruby@v1
32
- with:
33
- ruby-version: ${{ matrix.ruby }}
34
- - name: Update gems
35
- run: |
36
- gem install bundler
37
- bundle install --jobs 4 --retry 3
38
- - name: Run specs
39
- run: |
40
- bundle exec rake
41
- - name: Trigger repositories
42
- if: matrix.ruby == '2.6'
43
- env:
44
- GH_USERNAME: metanorma-ci
45
- GH_ACCESS_TOKEN: ${{ secrets.METANORMA_CI_PAT_TOKEN }}
46
- run: |
47
- curl -LO --retry 3 https://raw.githubusercontent.com/metanorma/metanorma-build-scripts/master/trigger-gh-actions.sh
48
- [[ -f ".github/workflows/dependent_repos.env" ]] && source .github/workflows/dependent_repos.env
49
- CLIENT_PAYLOAD=$(cat <<EOF
50
- "{ "ref": "${GITHUB_REF}", "repo": "${GITHUB_REPOSITORY}" }"
51
- EOF
52
- )
53
- for repo in $REPOS
54
- do
55
- sh trigger-gh-actions.sh $ORGANISATION $repo $GH_USERNAME $GH_ACCESS_TOKEN $GITHUB_REPOSITORY "$CLIENT_PAYLOAD"
56
- done
data/.github/workflows/windows.yml DELETED
@@ -1,40 +0,0 @@
1
- # Auto-generated by Cimas: Do not edit it manually!
2
- # See https://github.com/metanorma/cimas
3
- name: windows
4
-
5
- on:
6
- push:
7
- branches: [ master ]
8
- pull_request:
9
- paths-ignore:
10
- - .github/workflows/macos.yml
11
- - .github/workflows/ubuntu.yml
12
-
13
- jobs:
14
- test-windows:
15
- name: Test on Ruby ${{ matrix.ruby }} Windows
16
- runs-on: windows-latest
17
- continue-on-error: ${{ matrix.experimental }}
18
- strategy:
19
- fail-fast: false
20
- matrix:
21
- ruby: [ '2.6', '2.5', '2.4' ]
22
- experimental: [false]
23
- include:
24
- - ruby: '2.7'
25
- experimental: true
26
- steps:
27
- - uses: actions/checkout@master
28
- - name: Use Ruby
29
- uses: actions/setup-ruby@v1
30
- with:
31
- ruby-version: ${{ matrix.ruby }}
32
- - name: Update gems
33
- shell: pwsh
34
- run: |
35
- gem install bundler
36
- bundle config --local path vendor/bundle
37
- bundle install --jobs 4 --retry 3
38
- - name: Run specs
39
- run: |
40
- bundle exec rake