html2doc 1.1.1 → 1.2.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.github/workflows/rake.yml +1 -11
- data/.hound.yml +3 -1
- data/.rubocop.yml +4 -6
- data/README.adoc +2 -1
- data/bin/html2doc +1 -1
- data/bin/rspec +1 -1
- data/html2doc.gemspec +8 -9
- data/lib/html2doc/base.rb +4 -3
- data/lib/html2doc/lists.rb +24 -27
- data/lib/html2doc/math.rb +35 -18
- data/lib/html2doc/mime.rb +16 -17
- data/lib/html2doc/notes.rb +12 -9
- data/lib/html2doc/version.rb +1 -1
- data/lib/html2doc.rb +0 -3
- data/spec/html2doc_spec.rb +167 -121
- metadata +42 -42
data/spec/html2doc_spec.rb
CHANGED
|
@@ -64,11 +64,11 @@ WORD_HDR_END = <<~HDR.freeze
|
|
|
64
64
|
</head>
|
|
65
65
|
HDR
|
|
66
66
|
|
|
67
|
-
def word_body(
|
|
67
|
+
def word_body(xml, footnote)
|
|
68
68
|
<<~BODY
|
|
69
69
|
<body>
|
|
70
|
-
#{
|
|
71
|
-
#{
|
|
70
|
+
#{xml}
|
|
71
|
+
#{footnote}</body></html>
|
|
72
72
|
BODY
|
|
73
73
|
end
|
|
74
74
|
|
|
@@ -317,26 +317,36 @@ RSpec.describe Html2Doc do
|
|
|
317
317
|
end
|
|
318
318
|
|
|
319
319
|
it "processes a stylesheet in an HTML document with an empty head" do
|
|
320
|
-
Html2Doc.process(html_input_empty_head(""),
|
|
320
|
+
Html2Doc.process(html_input_empty_head(""),
|
|
321
|
+
filename: "test", stylesheet: "lib/html2doc/wordstyle.css")
|
|
322
|
+
word_hdr_end = WORD_HDR_END
|
|
323
|
+
.sub(%(<meta name="Originator" content="Me"/>\n), "")
|
|
324
|
+
.sub("</style>\n</head>", "</style></head>")
|
|
321
325
|
expect(guid_clean(File.read("test.doc", encoding: "utf-8")))
|
|
322
326
|
.to match_fuzzy(<<~OUTPUT)
|
|
323
327
|
#{WORD_HDR.sub('<title>blank</title>', '')}
|
|
324
328
|
#{DEFAULT_STYLESHEET}
|
|
325
|
-
#{
|
|
329
|
+
#{word_hdr_end}
|
|
326
330
|
#{word_body('', '<div style="mso-element:footnote-list"/>')} #{WORD_FTR1}
|
|
327
331
|
OUTPUT
|
|
328
332
|
end
|
|
329
333
|
|
|
330
334
|
it "processes a header" do
|
|
331
|
-
Html2Doc.process(html_input(""),
|
|
335
|
+
Html2Doc.process(html_input(""),
|
|
336
|
+
filename: "test", header_file: "spec/header.html")
|
|
332
337
|
html = guid_clean(File.read("test.doc", encoding: "utf-8"))
|
|
333
|
-
hdr = Base64.decode64(
|
|
334
|
-
|
|
335
|
-
|
|
338
|
+
hdr = Base64.decode64(
|
|
339
|
+
html
|
|
340
|
+
.sub(%r{^.*Content-Location: file:///C:/Doc/test_files/header.html}, "")
|
|
341
|
+
.sub(%r{^.*Content-Type: text/html charset="utf-8"}m, "")
|
|
342
|
+
.sub(%r{------=_NextPart_--.*$}m, ""),
|
|
343
|
+
).force_encoding("UTF-8")
|
|
336
344
|
# expect(hdr.gsub(/\xa0/, " ")).to match_fuzzy(HEADERHTML)
|
|
337
345
|
expect(HTMLEntities.new.encode(hdr, :hexadecimal)
|
|
338
|
-
|
|
339
|
-
|
|
346
|
+
.gsub(/</, "<").gsub(/>/, ">")
|
|
347
|
+
.gsub(/'/, "'").gsub(/"/, '"')
|
|
348
|
+
.gsub(/
/, "
").gsub(/
/, "\n"))
|
|
349
|
+
.to match_fuzzy(HEADERHTML)
|
|
340
350
|
expect(html.sub(%r{Content-ID: <header.html>.*$}m, ""))
|
|
341
351
|
.to match_fuzzy(<<~OUTPUT)
|
|
342
352
|
#{WORD_HDR} #{DEFAULT_STYLESHEET.gsub(/url\("[^"]+"\)/, 'url(cid:header.html)')}
|
|
@@ -345,7 +355,8 @@ RSpec.describe Html2Doc do
|
|
|
345
355
|
end
|
|
346
356
|
|
|
347
357
|
it "processes a header with an image" do
|
|
348
|
-
Html2Doc.process(html_input(""),
|
|
358
|
+
Html2Doc.process(html_input(""),
|
|
359
|
+
filename: "test", header_file: "spec/header_img.html")
|
|
349
360
|
doc = guid_clean(File.read("test.doc", encoding: "utf-8"))
|
|
350
361
|
expect(doc).to match(%r{Content-Type: image/png})
|
|
351
362
|
expect(doc).to match(%r{iVBORw0KGgoAAAANSUhEUgAAA5cAAAN7CAYAAADRE24cAAAgAElEQVR4XuydB5gUxdaGC65gTogB})
|
|
@@ -354,9 +365,13 @@ RSpec.describe Html2Doc do
|
|
|
354
365
|
it "processes a header with an image with absolute path" do
|
|
355
366
|
doc = File.read("spec/header_img.html", encoding: "utf-8")
|
|
356
367
|
File.open("spec/header_img1.html", "w:UTF-8") do |f|
|
|
357
|
-
f.write
|
|
368
|
+
f.write(
|
|
369
|
+
doc.sub(%r{spec/19160-6.png},
|
|
370
|
+
File.expand_path(File.join(File.dirname(__FILE__), "19160-6.png"))),
|
|
371
|
+
)
|
|
358
372
|
end
|
|
359
|
-
Html2Doc.process(html_input(""),
|
|
373
|
+
Html2Doc.process(html_input(""),
|
|
374
|
+
filename: "test", header_file: "spec/header_img1.html")
|
|
360
375
|
doc = guid_clean(File.read("test.doc", encoding: "utf-8"))
|
|
361
376
|
expect(doc).to match(%r{Content-Type: image/png})
|
|
362
377
|
expect(doc).to match(%r{iVBORw0KGgoAAAANSUhEUgAAA5cAAAN7CAYAAADRE24cAAAgAElEQVR4XuydB5gUxdaGC65gTogB})
|
|
@@ -375,43 +390,46 @@ RSpec.describe Html2Doc do
|
|
|
375
390
|
end
|
|
376
391
|
|
|
377
392
|
it "processes AsciiMath" do
|
|
378
|
-
Html2Doc.process(html_input(%[<div>{{sum_(i=1)^n i^3=((n(n+1))/2)^2 text("integer"))}}</div>]),
|
|
393
|
+
Html2Doc.process(html_input(%[<div>{{sum_(i=1)^n i^3=((n(n+1))/2)^2 text("integer"))}}</div>]),
|
|
394
|
+
filename: "test", asciimathdelims: ["{{", "}}"])
|
|
379
395
|
expect(guid_clean(File.read("test.doc", encoding: "utf-8")))
|
|
380
396
|
.to match_fuzzy(<<~OUTPUT)
|
|
381
397
|
#{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
|
|
382
398
|
#{word_body(%{
|
|
383
|
-
|
|
384
|
-
|
|
385
|
-
|
|
386
|
-
|
|
399
|
+
<div><m:oMath>
|
|
400
|
+
<m:nary><m:naryPr><m:chr m:val="∑"></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>
|
|
401
|
+
</m:oMath>
|
|
402
|
+
</div>}, '<div style="mso-element:footnote-list"/>')}
|
|
387
403
|
#{WORD_FTR1}
|
|
388
404
|
OUTPUT
|
|
389
405
|
end
|
|
390
406
|
|
|
391
407
|
it "processes mstyle" do
|
|
392
|
-
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>]),
|
|
408
|
+
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>]),
|
|
409
|
+
filename: "test", asciimathdelims: ["{{", "}}"])
|
|
393
410
|
expect(guid_clean(File.read("test.doc", encoding: "utf-8")))
|
|
394
411
|
.to match_fuzzy(<<~OUTPUT)
|
|
395
412
|
#{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
|
|
396
413
|
#{word_body(%{
|
|
397
|
-
|
|
398
|
-
|
|
399
|
-
|
|
400
|
-
|
|
414
|
+
<div><m:oMath>
|
|
415
|
+
<span style="font-style:normal;font-weight:bold;"><m:r><m:rPr><m:sty m:val="b"></m:sty></m:rPr><m:t>−</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>𝔹𝔹𝔹</m:t></m:r><m:r><m:rPr><m:nor></m:nor><m:scr m:val="script"></m:scr></m:rPr><m:t>𝒞𝒞</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>𝓑𝓒𝓒</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>𝚃𝚃</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>𝔉ℜ</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>𝕭𝕱𝕽</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>𝖲𝖥</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>𝗕𝗦𝗙𝝰</m:t></m:r><m:r><m:rPr><m:nor></m:nor><m:scr m:val="sans-serif"></m:scr></m:rPr><m:t>𝖲𝖥𝖨</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>𝙎𝙁𝘽𝙄𝞪</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>
|
|
416
|
+
</m:oMath>
|
|
417
|
+
</div>}, '<div style="mso-element:footnote-list"/>')}
|
|
401
418
|
#{WORD_FTR1}
|
|
402
419
|
OUTPUT
|
|
403
420
|
end
|
|
404
421
|
|
|
405
422
|
it "processes spaces in AsciiMath" do
|
|
406
|
-
Html2Doc.process(html_input(%[<div>{{text " integer ")}}</div>]),
|
|
423
|
+
Html2Doc.process(html_input(%[<div>{{text " integer ")}}</div>]),
|
|
424
|
+
filename: "test", asciimathdelims: ["{{", "}}"])
|
|
407
425
|
expect(guid_clean(File.read("test.doc", encoding: "utf-8")))
|
|
408
426
|
.to match_fuzzy(<<~OUTPUT)
|
|
409
427
|
#{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
|
|
410
428
|
#{word_body('
|
|
411
|
-
|
|
412
|
-
|
|
413
|
-
|
|
414
|
-
|
|
429
|
+
<div><m:oMath>
|
|
430
|
+
<m:r><m:t>text</m:t></m:r><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>
|
|
431
|
+
</m:oMath>
|
|
432
|
+
</div>', '<div style="mso-element:footnote-list"/>')}
|
|
415
433
|
#{WORD_FTR1}
|
|
416
434
|
OUTPUT
|
|
417
435
|
end
|
|
@@ -419,14 +437,15 @@ RSpec.describe Html2Doc do
|
|
|
419
437
|
it "processes spaces in MathML mtext" do
|
|
420
438
|
Html2Doc.process(html_input("<div><math xmlns='http://www.w3.org/1998/Math/MathML'>
|
|
421
439
|
<mrow><mi>H</mi><mtext> original </mtext><mi>J</mi></mrow>
|
|
422
|
-
</math></div>"),
|
|
440
|
+
</math></div>"),
|
|
441
|
+
filename: "test", asciimathdelims: ["{{", "}}"])
|
|
423
442
|
expect(guid_clean(File.read("test.doc", encoding: "utf-8")))
|
|
424
443
|
.to match_fuzzy(<<~OUTPUT)
|
|
425
444
|
#{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
|
|
426
445
|
#{word_body('<div><m:oMath>
|
|
427
|
-
|
|
428
|
-
|
|
429
|
-
|
|
446
|
+
<m:r><m:t>H</m:t></m:r><m:r><m:rPr><m:nor></m:nor></m:rPr><m:t> original </m:t></m:r><m:r><m:t>J</m:t></m:r>
|
|
447
|
+
</m:oMath>
|
|
448
|
+
</div>', '<div style="mso-element:footnote-list"/>')}
|
|
430
449
|
#{WORD_FTR1}
|
|
431
450
|
OUTPUT
|
|
432
451
|
end
|
|
@@ -439,58 +458,67 @@ RSpec.describe Html2Doc do
|
|
|
439
458
|
.to match_fuzzy(<<~OUTPUT)
|
|
440
459
|
#{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
|
|
441
460
|
#{word_body('<div><m:oMath>
|
|
442
|
-
|
|
443
|
-
|
|
444
|
-
|
|
461
|
+
<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>
|
|
462
|
+
</m:oMath>
|
|
463
|
+
</div>', '<div style="mso-element:footnote-list"/>')}
|
|
445
464
|
#{WORD_FTR1}
|
|
446
465
|
OUTPUT
|
|
447
466
|
end
|
|
448
467
|
|
|
449
468
|
it "left-aligns AsciiMath" do
|
|
450
|
-
Html2Doc.process(html_input("<div style='text-align:left;'>{{sum_(i=1)^n i^3=((n(n+1))/2)^2}}</div>"),
|
|
469
|
+
Html2Doc.process(html_input("<div style='text-align:left;'>{{sum_(i=1)^n i^3=((n(n+1))/2)^2}}</div>"),
|
|
470
|
+
filename: "test", asciimathdelims: ["{{", "}}"])
|
|
451
471
|
expect(guid_clean(File.read("test.doc", encoding: "utf-8")))
|
|
452
472
|
.to match_fuzzy(<<~OUTPUT)
|
|
453
473
|
#{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
|
|
454
474
|
#{word_body(%{
|
|
455
|
-
|
|
456
|
-
|
|
457
|
-
|
|
458
|
-
|
|
475
|
+
<div style="text-align:left;"><m:oMathPara><m:oMathParaPr><m:jc m:val="left"/></m:oMathParaPr><m:oMath>
|
|
476
|
+
<m:nary><m:naryPr><m:chr m:val="∑"></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>
|
|
477
|
+
</m:oMath>
|
|
478
|
+
</m:oMathPara></div>}, '<div style="mso-element:footnote-list"/>')}
|
|
459
479
|
#{WORD_FTR1}
|
|
460
480
|
OUTPUT
|
|
461
481
|
end
|
|
462
482
|
|
|
463
483
|
it "right-aligns AsciiMath" do
|
|
464
|
-
Html2Doc.process(html_input("<div style='text-align:right;'>{{sum_(i=1)^n i^3=((n(n+1))/2)^2}}</div>"),
|
|
484
|
+
Html2Doc.process(html_input("<div style='text-align:right;'>{{sum_(i=1)^n i^3=((n(n+1))/2)^2}}</div>"),
|
|
485
|
+
filename: "test", asciimathdelims: ["{{", "}}"])
|
|
465
486
|
expect(guid_clean(File.read("test.doc", encoding: "utf-8")))
|
|
466
487
|
.to match_fuzzy(<<~OUTPUT)
|
|
467
488
|
#{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
|
|
468
489
|
#{word_body(%{
|
|
469
|
-
|
|
470
|
-
|
|
471
|
-
|
|
472
|
-
|
|
490
|
+
<div style="text-align:right;"><m:oMathPara><m:oMathParaPr><m:jc m:val="right"/></m:oMathParaPr><m:oMath>
|
|
491
|
+
<m:nary><m:naryPr><m:chr m:val="∑"></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>
|
|
492
|
+
</m:oMath>
|
|
493
|
+
</m:oMathPara></div>}, '<div style="mso-element:footnote-list"/>')}
|
|
473
494
|
#{WORD_FTR1}
|
|
474
495
|
OUTPUT
|
|
475
496
|
end
|
|
476
497
|
|
|
477
498
|
it "raises error in processing of broken AsciiMath" do
|
|
478
499
|
begin
|
|
479
|
-
expect
|
|
500
|
+
expect do
|
|
501
|
+
Html2Doc.process(html_input(%[<div style='text-align:right;'>{{u_c = 6.6"unitsml(kHz)}}</div>]),
|
|
502
|
+
filename: "test", asciimathdelims: ["{{", "}}"])
|
|
503
|
+
end.to output('parsing: u_c = 6.6"unitsml(kHz)').to_stderr
|
|
480
504
|
rescue StandardError
|
|
481
505
|
end
|
|
482
|
-
expect
|
|
506
|
+
expect do
|
|
507
|
+
Html2Doc.process(html_input(%[<div style='text-align:right;'>{{u_c = 6.6"unitsml(kHz)}}</div>]),
|
|
508
|
+
filename: "test", asciimathdelims: ["{{", "}}"])
|
|
509
|
+
end.to raise_error(StandardError)
|
|
483
510
|
end
|
|
484
511
|
|
|
485
512
|
it "wraps msup after munderover in MathML" do
|
|
486
513
|
Html2Doc.process(html_input("<div><math xmlns='http://www.w3.org/1998/Math/MathML'>
|
|
487
|
-
<munderover><mo>∑</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>"),
|
|
514
|
+
<munderover><mo>∑</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>"),
|
|
515
|
+
filename: "test", asciimathdelims: ["{{", "}}"])
|
|
488
516
|
expect(guid_clean(File.read("test.doc", encoding: "utf-8")))
|
|
489
517
|
.to match_fuzzy(<<~OUTPUT)
|
|
490
518
|
#{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
|
|
491
519
|
#{word_body('<div><m:oMath>
|
|
492
|
-
|
|
493
|
-
|
|
520
|
+
<m:nary><m:naryPr><m:chr m:val="∑"></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=0</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>2</m:t></m:r></m:e><m:sup><m:r><m:t>i</m:t></m:r></m:sup></m:sSup></m:e></m:nary></m:oMath>
|
|
521
|
+
</div>', '<div style="mso-element:footnote-list"/>')}
|
|
494
522
|
#{WORD_FTR1}
|
|
495
523
|
OUTPUT
|
|
496
524
|
end
|
|
@@ -537,7 +565,7 @@ RSpec.describe Html2Doc do
|
|
|
537
565
|
|
|
538
566
|
it "resizes images for height, in a file in a subdirectory" do
|
|
539
567
|
simple_body = '<img src="19160-6.png">'
|
|
540
|
-
Html2Doc.process(html_input(simple_body), filename: "spec/test")
|
|
568
|
+
Html2Doc.process(html_input(simple_body), filename: "spec/test", imagedir: "spec")
|
|
541
569
|
testdoc = File.read("spec/test.doc", encoding: "utf-8")
|
|
542
570
|
expect(testdoc).to match(%r{Content-Type: image/png})
|
|
543
571
|
expect(image_clean(guid_clean(testdoc))).to match_fuzzy(<<~OUTPUT)
|
|
@@ -549,7 +577,7 @@ RSpec.describe Html2Doc do
|
|
|
549
577
|
|
|
550
578
|
it "resizes images for width" do
|
|
551
579
|
simple_body = '<img src="spec/19160-7.gif">'
|
|
552
|
-
Html2Doc.process(html_input(simple_body), filename: "test")
|
|
580
|
+
Html2Doc.process(html_input(simple_body), filename: "test", imagedir: ".")
|
|
553
581
|
testdoc = File.read("test.doc", encoding: "utf-8")
|
|
554
582
|
expect(testdoc).to match(%r{Content-Type: image/gif})
|
|
555
583
|
expect(image_clean(guid_clean(testdoc))).to match_fuzzy(<<~OUTPUT)
|
|
@@ -561,7 +589,7 @@ RSpec.describe Html2Doc do
|
|
|
561
589
|
|
|
562
590
|
it "resizes images for height" do
|
|
563
591
|
simple_body = '<img src="spec/19160-8.jpg">'
|
|
564
|
-
Html2Doc.process(html_input(simple_body), filename: "test")
|
|
592
|
+
Html2Doc.process(html_input(simple_body), filename: "test", imagedir: ".")
|
|
565
593
|
testdoc = File.read("test.doc", encoding: "utf-8")
|
|
566
594
|
expect(testdoc).to match(%r{Content-Type: image/jpeg})
|
|
567
595
|
expect(image_clean(guid_clean(testdoc))).to match_fuzzy(<<~OUTPUT)
|
|
@@ -573,38 +601,48 @@ RSpec.describe Html2Doc do
|
|
|
573
601
|
|
|
574
602
|
it "resizes images with missing or auto sizes" do
|
|
575
603
|
image = { "src" => "spec/19160-8.jpg" }
|
|
576
|
-
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
604
|
+
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
605
|
+
.to eq [30, 100]
|
|
577
606
|
image["width"] = "20"
|
|
578
|
-
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
607
|
+
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
608
|
+
.to eq [20, 65]
|
|
579
609
|
image.delete("width")
|
|
580
610
|
image["height"] = "50"
|
|
581
|
-
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
611
|
+
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
612
|
+
.to eq [15, 50]
|
|
582
613
|
image.delete("height")
|
|
583
614
|
image["width"] = "500"
|
|
584
|
-
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
615
|
+
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
616
|
+
.to eq [30, 100]
|
|
585
617
|
image.delete("width")
|
|
586
618
|
image["height"] = "500"
|
|
587
|
-
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
619
|
+
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
620
|
+
.to eq [30, 100]
|
|
588
621
|
image["width"] = "20"
|
|
589
622
|
image["height"] = "auto"
|
|
590
|
-
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
623
|
+
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
624
|
+
.to eq [20, 65]
|
|
591
625
|
image["width"] = "auto"
|
|
592
626
|
image["height"] = "50"
|
|
593
|
-
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
627
|
+
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
628
|
+
.to eq [15, 50]
|
|
594
629
|
image["width"] = "500"
|
|
595
630
|
image["height"] = "auto"
|
|
596
|
-
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
631
|
+
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
632
|
+
.to eq [30, 100]
|
|
597
633
|
image["width"] = "auto"
|
|
598
634
|
image["height"] = "500"
|
|
599
|
-
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
635
|
+
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
636
|
+
.to eq [30, 100]
|
|
600
637
|
image["width"] = "auto"
|
|
601
638
|
image["height"] = "auto"
|
|
602
|
-
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
639
|
+
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
640
|
+
.to eq [30, 100]
|
|
603
641
|
end
|
|
604
642
|
|
|
605
643
|
it "does not move images if they are external URLs" do
|
|
606
644
|
simple_body = '<img src="https://example.com/19160-6.png">'
|
|
607
|
-
Html2Doc.process(html_input(simple_body), filename: "test")
|
|
645
|
+
Html2Doc.process(html_input(simple_body), filename: "test", imagedir: ".")
|
|
608
646
|
testdoc = File.read("test.doc", encoding: "utf-8")
|
|
609
647
|
expect(image_clean(guid_clean(testdoc))).to match_fuzzy(<<~OUTPUT)
|
|
610
648
|
#{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
|
|
@@ -615,7 +653,7 @@ RSpec.describe Html2Doc do
|
|
|
615
653
|
|
|
616
654
|
it "deals with absolute image locations" do
|
|
617
655
|
simple_body = %{<img src="#{__dir__}/19160-6.png">}
|
|
618
|
-
Html2Doc.process(html_input(simple_body), filename: "spec/test")
|
|
656
|
+
Html2Doc.process(html_input(simple_body), filename: "spec/test", imagedir: ".")
|
|
619
657
|
testdoc = File.read("spec/test.doc", encoding: "utf-8")
|
|
620
658
|
expect(testdoc).to match(%r{Content-Type: image/png})
|
|
621
659
|
expect(image_clean(guid_clean(testdoc))).to match_fuzzy(<<~OUTPUT)
|
|
@@ -627,7 +665,8 @@ RSpec.describe Html2Doc do
|
|
|
627
665
|
|
|
628
666
|
# it "warns about SVG" do
|
|
629
667
|
# simple_body = '<img src="https://example.com/19160-6.svg">'
|
|
630
|
-
# expect{ Html2Doc.process(html_input(simple_body), filename: "test") }
|
|
668
|
+
# expect{ Html2Doc.process(html_input(simple_body), filename: "test") }
|
|
669
|
+
# .to output("https://example.com/19160-6.svg: SVG not supported\n").to_stderr
|
|
631
670
|
# end
|
|
632
671
|
|
|
633
672
|
it "processes epub:type footnotes" do
|
|
@@ -638,15 +677,15 @@ RSpec.describe Html2Doc do
|
|
|
638
677
|
Html2Doc.process(html_input(simple_body), filename: "test")
|
|
639
678
|
expect(guid_clean(File.read("test.doc", encoding: "utf-8")))
|
|
640
679
|
.to match_fuzzy(<<~OUTPUT)
|
|
641
|
-
|
|
642
|
-
|
|
643
|
-
|
|
644
|
-
|
|
645
|
-
|
|
646
|
-
|
|
647
|
-
|
|
648
|
-
|
|
649
|
-
|
|
680
|
+
#{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
|
|
681
|
+
#{word_body('<div>This is a very simple
|
|
682
|
+
document<a epub:type="footnote" href="#_ftn1" style="mso-footnote-id:ftn1" name="_ftnref1" title="" id="_ftnref1"><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span></a> allegedly<a epub:type="footnote" href="#_ftn2" style="mso-footnote-id:ftn2" name="_ftnref2" title="" id="_ftnref2"><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span></a></div>',
|
|
683
|
+
'<div style="mso-element:footnote-list"><div style="mso-element:footnote" id="ftn1">
|
|
684
|
+
<p id="" class="MsoFootnoteText"><a style="mso-footnote-id:ftn1" href="#_ftn1" name="_ftnref1" title="" id="_ftnref1"><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span></a>Footnote</p></div>
|
|
685
|
+
<div style="mso-element:footnote" id="ftn2">
|
|
686
|
+
<p id="" class="MsoFootnoteText"><a style="mso-footnote-id:ftn2" href="#_ftn2" name="_ftnref2" title="" id="_ftnref2"><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span></a>Other Footnote</p></div>
|
|
687
|
+
</div>')}
|
|
688
|
+
#{WORD_FTR1}
|
|
650
689
|
OUTPUT
|
|
651
690
|
end
|
|
652
691
|
|
|
@@ -658,15 +697,15 @@ RSpec.describe Html2Doc do
|
|
|
658
697
|
Html2Doc.process(html_input(simple_body), filename: "test")
|
|
659
698
|
expect(guid_clean(File.read("test.doc", encoding: "utf-8")))
|
|
660
699
|
.to match_fuzzy(<<~OUTPUT)
|
|
661
|
-
|
|
662
|
-
|
|
663
|
-
|
|
664
|
-
|
|
665
|
-
|
|
666
|
-
|
|
667
|
-
|
|
668
|
-
|
|
669
|
-
|
|
700
|
+
#{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
|
|
701
|
+
#{word_body('<div>This is a very simple
|
|
702
|
+
document<a class="footnote" href="#_ftn1" style="mso-footnote-id:ftn1" name="_ftnref1" title="" id="_ftnref1"><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span></a> allegedly<a class="footnote" href="#_ftn2" style="mso-footnote-id:ftn2" name="_ftnref2" title="" id="_ftnref2"><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span></a></div>',
|
|
703
|
+
'<div style="mso-element:footnote-list"><div style="mso-element:footnote" id="ftn1">
|
|
704
|
+
<p id="" class="MsoFootnoteText"><a style="mso-footnote-id:ftn1" href="#_ftn1" name="_ftnref1" title="" id="_ftnref1"><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span></a>Footnote</p></div>
|
|
705
|
+
<div style="mso-element:footnote" id="ftn2">
|
|
706
|
+
<p id="" class="MsoFootnoteText"><a style="mso-footnote-id:ftn2" href="#_ftn2" name="_ftnref2" title="" id="_ftnref2"><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span></a>Other Footnote</p></div>
|
|
707
|
+
</div>')}
|
|
708
|
+
#{WORD_FTR1}
|
|
670
709
|
OUTPUT
|
|
671
710
|
end
|
|
672
711
|
|
|
@@ -678,15 +717,15 @@ RSpec.describe Html2Doc do
|
|
|
678
717
|
Html2Doc.process(html_input(simple_body), filename: "test")
|
|
679
718
|
expect(guid_clean(File.read("test.doc", encoding: "utf-8")))
|
|
680
719
|
.to match_fuzzy(<<~OUTPUT)
|
|
681
|
-
|
|
682
|
-
|
|
683
|
-
|
|
684
|
-
|
|
685
|
-
|
|
686
|
-
|
|
687
|
-
|
|
688
|
-
|
|
689
|
-
|
|
720
|
+
#{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
|
|
721
|
+
#{word_body('<div>This is a very simple
|
|
722
|
+
document<a class="footnote" href="#_ftn1" style="mso-footnote-id:ftn1" name="_ftnref1" title="" id="_ftnref1"><span class="MsoFootnoteReference">(</span><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span><span class="MsoFootnoteReference">)</span></a> allegedly<a class="footnote" href="#_ftn2" style="mso-footnote-id:ftn2" name="_ftnref2" title="" id="_ftnref2"><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span></a></div>',
|
|
723
|
+
'<div style="mso-element:footnote-list"><div style="mso-element:footnote" id="ftn1">
|
|
724
|
+
<p id="" class="MsoFootnoteText"><a style="mso-footnote-id:ftn1" href="#_ftn1" name="_ftnref1" title="" id="_ftnref1"><span class="MsoFootnoteReference">(</span><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span><span class="MsoFootnoteReference">)</span></a>Footnote</p></div>
|
|
725
|
+
<div style="mso-element:footnote" id="ftn2">
|
|
726
|
+
<p id="" class="MsoFootnoteText"><a style="mso-footnote-id:ftn2" href="#_ftn2" name="_ftnref2" title="" id="_ftnref2"><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span></a>Other Footnote</p></div>
|
|
727
|
+
</div>')}
|
|
728
|
+
#{WORD_FTR1}
|
|
690
729
|
OUTPUT
|
|
691
730
|
end
|
|
692
731
|
|
|
@@ -698,15 +737,15 @@ RSpec.describe Html2Doc do
|
|
|
698
737
|
Html2Doc.process(html_input(simple_body), filename: "test")
|
|
699
738
|
expect(guid_clean(File.read("test.doc", encoding: "utf-8")))
|
|
700
739
|
.to match_fuzzy(<<~OUTPUT)
|
|
701
|
-
|
|
702
|
-
|
|
703
|
-
|
|
704
|
-
|
|
705
|
-
|
|
706
|
-
|
|
707
|
-
|
|
708
|
-
|
|
709
|
-
|
|
740
|
+
#{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
|
|
741
|
+
#{word_body('<div>This is a very simple
|
|
742
|
+
document<a class="footnote" href="#_ftn1" style="mso-footnote-id:ftn1" name="_ftnref1" title="" id="_ftnref1"><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span></a> allegedly<a class="footnote" href="#_ftn2" style="mso-footnote-id:ftn2" name="_ftnref2" title="" id="_ftnref2"><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span></a></div>',
|
|
743
|
+
'<div style="mso-element:footnote-list"><div style="mso-element:footnote" id="ftn1">
|
|
744
|
+
<p class="MsoFootnoteText"><a style="mso-footnote-id:ftn1" href="#_ftn1" name="_ftnref1" title="" id="_ftnref1"><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span></a>Footnote</p></div>
|
|
745
|
+
<div style="mso-element:footnote" id="ftn2">
|
|
746
|
+
<p class="MsoFootnoteText"><a style="mso-footnote-id:ftn2" href="#_ftn2" name="_ftnref2" title="" id="_ftnref2"><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span></a>Other Footnote</p></div>
|
|
747
|
+
</div>')}
|
|
748
|
+
#{WORD_FTR1}
|
|
710
749
|
OUTPUT
|
|
711
750
|
end
|
|
712
751
|
|
|
@@ -715,13 +754,14 @@ RSpec.describe Html2Doc do
|
|
|
715
754
|
<div><ul id="0">
|
|
716
755
|
<li><div><p><ol id="1"><li><ul id="2"><li><p><ol id="3"><li><ol id="4"><li>A</li><li><p>B</p><p>B2</p></li><li>C</li></ol></li></ol></p></li></ul></li></ol></p></div></li><div><ul id="5"><li>C</li></ul></div>
|
|
717
756
|
BODY
|
|
718
|
-
Html2Doc.process(html_input(simple_body),
|
|
757
|
+
Html2Doc.process(html_input(simple_body),
|
|
758
|
+
filename: "test", liststyles: { ul: "l1", ol: "l2" })
|
|
719
759
|
expect(guid_clean(File.read("test.doc", encoding: "utf-8")))
|
|
720
760
|
.to match_fuzzy(<<~OUTPUT)
|
|
721
761
|
#{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
|
|
722
762
|
#{word_body('<div>
|
|
723
|
-
|
|
724
|
-
|
|
763
|
+
<p style="mso-list:l1 level1 lfo1;" class="MsoListParagraphCxSpFirst"><div><p class="MsoNormal"><p style="mso-list:l2 level2 lfo1;" class="MsoListParagraphCxSpFirst"><p style="mso-list:l2 level4 lfo1;" class="MsoListParagraphCxSpFirst"><p style="mso-list:l2 level5 lfo1;" class="MsoListParagraphCxSpFirst">A</p><p style="mso-list:l2 level5 lfo1;" class="MsoListParagraphCxSpMiddle">B<p class="MsoListParagraphCxSpMiddle">B2</p></p><p style="mso-list:l2 level5 lfo1;" class="MsoListParagraphCxSpLast">C</p></p></p></p></div></p><div><p style="mso-list:l1 level1 lfo2;" class="MsoListParagraphCxSpFirst">C</p></div>
|
|
764
|
+
</div>',
|
|
725
765
|
'<div style="mso-element:footnote-list"/>')}
|
|
726
766
|
#{WORD_FTR1}
|
|
727
767
|
OUTPUT
|
|
@@ -733,13 +773,14 @@ RSpec.describe Html2Doc do
|
|
|
733
773
|
<ol id="1"><li><div><p><ol id="2"><li><ul id="3"><li><p><ol id="4"><li><ol id="5"><li>A</li></ol></li></ol></p></li></ul></li></ol></p></div></li></ol>
|
|
734
774
|
<ol id="6"><li><div><p><ol id="7"><li><ul id="8"><li><p><ol id="9"><li><ol id="10"><li>A</li></ol></li></ol></p></li></ul></li></ol></p></div></li></ol></div>
|
|
735
775
|
BODY
|
|
736
|
-
Html2Doc.process(html_input(simple_body),
|
|
776
|
+
Html2Doc.process(html_input(simple_body),
|
|
777
|
+
filename: "test", liststyles: { ul: "l1", ol: "l2" })
|
|
737
778
|
expect(guid_clean(File.read("test.doc", encoding: "utf-8")))
|
|
738
779
|
.to match_fuzzy(<<~OUTPUT)
|
|
739
780
|
#{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
|
|
740
781
|
#{word_body('<div>
|
|
741
|
-
|
|
742
|
-
|
|
782
|
+
<p style="mso-list:l2 level1 lfo1;" class="MsoListParagraphCxSpFirst"><div><p class="MsoNormal"><p style="mso-list:l2 level2 lfo1;" class="MsoListParagraphCxSpFirst"><p style="mso-list:l2 level4 lfo1;" class="MsoListParagraphCxSpFirst"><p style="mso-list:l2 level5 lfo1;" class="MsoListParagraphCxSpFirst">A</p></p></p></p></div></p>
|
|
783
|
+
<p style="mso-list:l2 level1 lfo2;" class="MsoListParagraphCxSpFirst"><div><p class="MsoNormal"><p style="mso-list:l2 level2 lfo2;" class="MsoListParagraphCxSpFirst"><p style="mso-list:l2 level4 lfo2;" class="MsoListParagraphCxSpFirst"><p style="mso-list:l2 level5 lfo2;" class="MsoListParagraphCxSpFirst">A</p></p></p></p></div></p></div>',
|
|
743
784
|
'<div style="mso-element:footnote-list"/>')}
|
|
744
785
|
#{WORD_FTR1}
|
|
745
786
|
OUTPUT
|
|
@@ -754,16 +795,18 @@ RSpec.describe Html2Doc do
|
|
|
754
795
|
<div><ul class="other" id="10">
|
|
755
796
|
<li><div><p><ol id="11"><li><ul id="12"><li><p><ol id="13"><li><ol id="14"><li>A</li><li><p>B</p><p>B2</p></li><li>C</li></ol></li></ol></p></li></ul></li></ol></p></div></li></ul></div>
|
|
756
797
|
BODY
|
|
757
|
-
Html2Doc.process(html_input(simple_body),
|
|
798
|
+
Html2Doc.process(html_input(simple_body),
|
|
799
|
+
filename: "test",
|
|
800
|
+
liststyles: { ul: "l1", ol: "l2", steps: "l3" })
|
|
758
801
|
expect(guid_clean(File.read("test.doc", encoding: "utf-8")))
|
|
759
802
|
.to match_fuzzy(<<~OUTPUT)
|
|
760
803
|
#{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
|
|
761
804
|
#{word_body('<div>
|
|
762
|
-
|
|
763
|
-
|
|
764
|
-
|
|
765
|
-
|
|
766
|
-
|
|
805
|
+
<p style="mso-list:l3 level1 lfo2;" class="MsoListParagraphCxSpFirst"><div><p class="MsoNormal"><p style="mso-list:l3 level2 lfo2;" class="MsoListParagraphCxSpFirst"><p style="mso-list:l3 level4 lfo2;" class="MsoListParagraphCxSpFirst"><p style="mso-list:l3 level5 lfo2;" class="MsoListParagraphCxSpFirst">A</p><p style="mso-list:l3 level5 lfo2;" class="MsoListParagraphCxSpMiddle">B<p class="MsoListParagraphCxSpMiddle">B2</p></p><p style="mso-list:l3 level5 lfo2;" class="MsoListParagraphCxSpLast">C</p></p></p></p></div></p></div>
|
|
806
|
+
<div>
|
|
807
|
+
<p style="mso-list:l1 level1 lfo1;" class="MsoListParagraphCxSpFirst"><div><p class="MsoNormal"><p style="mso-list:l2 level2 lfo1;" class="MsoListParagraphCxSpFirst"><p style="mso-list:l2 level4 lfo1;" class="MsoListParagraphCxSpFirst"><p style="mso-list:l2 level5 lfo1;" class="MsoListParagraphCxSpFirst">A</p><p style="mso-list:l2 level5 lfo1;" class="MsoListParagraphCxSpMiddle">B<p class="MsoListParagraphCxSpMiddle">B2</p></p><p style="mso-list:l2 level5 lfo1;" class="MsoListParagraphCxSpLast">C</p></p></p></p></div></p></div>
|
|
808
|
+
<div>
|
|
809
|
+
<p style="mso-list:l1 level1 lfo3;" class="MsoListParagraphCxSpFirst"><div><p class="MsoNormal"><p style="mso-list:l2 level2 lfo3;" class="MsoListParagraphCxSpFirst"><p style="mso-list:l2 level4 lfo3;" class="MsoListParagraphCxSpFirst"><p style="mso-list:l2 level5 lfo3;" class="MsoListParagraphCxSpFirst">A</p><p style="mso-list:l2 level5 lfo3;" class="MsoListParagraphCxSpMiddle">B<p class="MsoListParagraphCxSpMiddle">B2</p></p><p style="mso-list:l2 level5 lfo3;" class="MsoListParagraphCxSpLast">C</p></p></p></p></div></p></div>',
|
|
767
810
|
'<div style="mso-element:footnote-list"/>')}
|
|
768
811
|
#{WORD_FTR1}
|
|
769
812
|
OUTPUT
|
|
@@ -776,14 +819,15 @@ RSpec.describe Html2Doc do
|
|
|
776
819
|
<p id="b"/>
|
|
777
820
|
</div>
|
|
778
821
|
BODY
|
|
779
|
-
Html2Doc.process(html_input(simple_body),
|
|
822
|
+
Html2Doc.process(html_input(simple_body),
|
|
823
|
+
filename: "test", liststyles: { ul: "l1", ol: "l2" })
|
|
780
824
|
expect(guid_clean(File.read("test.doc", encoding: "utf-8")))
|
|
781
825
|
.to match_fuzzy(<<~OUTPUT)
|
|
782
826
|
#{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
|
|
783
827
|
#{word_body('<div>
|
|
784
|
-
|
|
785
|
-
|
|
786
|
-
|
|
828
|
+
<p class="MsoNormal"><a name="a" id="a"></a>Hello</p>
|
|
829
|
+
<p class="MsoNormal"><a name="b" id="b"></a></p>
|
|
830
|
+
</div>',
|
|
787
831
|
'<div style="mso-element:footnote-list"/>')}
|
|
788
832
|
#{WORD_FTR1}
|
|
789
833
|
OUTPUT
|
|
@@ -791,12 +835,14 @@ RSpec.describe Html2Doc do
|
|
|
791
835
|
|
|
792
836
|
it "test image base64 image encoding" do
|
|
793
837
|
simple_body = '<img src="19160-6.png">'
|
|
794
|
-
Html2Doc.process(html_input(simple_body),
|
|
838
|
+
Html2Doc.process(html_input(simple_body),
|
|
839
|
+
filename: "spec/test", debug: true, imagedir: "spec")
|
|
795
840
|
testdoc = File.read("spec/test.doc", encoding: "utf-8")
|
|
796
841
|
base64_image = testdoc[/image\/png\n\n(.*?)\n\n----/m, 1].gsub!("\n", "")
|
|
797
842
|
base64_image_basename = testdoc[%r{Content-ID: <([0-9a-z\-]+)\.png}m, 1]
|
|
798
843
|
doc_bin_image = Base64.strict_decode64(base64_image)
|
|
799
|
-
file_bin_image = IO
|
|
844
|
+
file_bin_image = IO
|
|
845
|
+
.read("spec/test_files/#{base64_image_basename}.png", mode: "rb")
|
|
800
846
|
expect(doc_bin_image).to eq file_bin_image
|
|
801
847
|
FileUtils.rm_rf %w[spec/test_files spec/test.doc spec/test.htm]
|
|
802
848
|
end
|