Skip to content

Commit 0400706

Browse files
iText-CIiText-CI
committed
[RELEASE] iText 7 pdfOcr - 1.0.1
https://git.itextsupport.com/ * release/1.0.1: [RELEASE] 1.0.1-SNAPSHOT -> 1.0.1 Update autoported files Synchronized collections to avoid test failures Get rid of $(SolutionDir) in csproj files Update autoported files Remove unused fields Improvements in word bbox calculation Update port-hash Update port-hash Add project references to iText dependencies - Tweaked the product description - Added the product website - Added the GitHub repo Refactor the path to tessdata so that it doesn't end with a slash Remove irrelevant comment Minor Javadoc fix Update port-hash after release [RELEASE] Update dependency versions
2 parents 30d7642 + d0586e3 commit 0400706

31 files changed

+298
-182
lines changed

‎doxyfile

+1-1
Original file line numberDiff line numberDiff line change
@@ -32,7 +32,7 @@ DOXYFILE_ENCODING = UTF-8
3232
# title of most generated pages and in a few other places.
3333
# The default value is: My Project.
3434

35-
PROJECT_NAME = "pdfOCR VERSION_PLACEHOLDER API"
35+
PROJECT_NAME = "pdfOCR 1.0.1 API"
3636

3737
# The PROJECT_NUMBER tag can be used to enter a project or revision number. This
3838
# could be handy for archiving the generated documentation or if some version

‎itext.tests/itext.pdfocr.api.tests/Properties/AssemblyInfo.cs

+3-3
Original file line numberDiff line numberDiff line change
@@ -15,6 +15,6 @@
1515

1616
[assembly: Guid("d6a6ea97-1f23-448f-b700-eff62971d234")]
1717

18-
[assembly: AssemblyVersion("1.0.0.0")]
19-
[assembly: AssemblyFileVersion("1.0.0.0")]
20-
[assembly: AssemblyInformationalVersion("1.0.0")]
18+
[assembly: AssemblyVersion("1.0.1.0")]
19+
[assembly: AssemblyFileVersion("1.0.1.0")]
20+
[assembly: AssemblyInformationalVersion("1.0.1")]

‎itext.tests/itext.pdfocr.api.tests/itext.pdfocr.api.tests.csproj

+3-2
Original file line numberDiff line numberDiff line change
@@ -26,7 +26,8 @@
2626
<None Include="itext.snk" />
2727
</ItemGroup>
2828
<ItemGroup>
29-
<PackageReference Include="itext7.pdftest" Version="7.1.11" />
29+
<ProjectReference Include="..\..\..\itextcore\itext\itext.pdftest\itext.pdftest.netstandard.csproj" Condition="Exists('..\..\..\itextcore\itext\itext.pdftest\itext.pdftest.netstandard.csproj')" />
30+
<PackageReference Include="itext7.pdftest" Version="7.1.12" Condition="!Exists('..\..\..\itextcore\itext\itext.pdftest\itext.pdftest.netstandard.csproj')" />
3031
<PackageReference Include="Microsoft.NET.Test.Sdk" Version="16.6.0" />
3132
<PackageReference Include="NUnit" Version="3.12.0" />
3233
<PackageReference Include="NUnit3TestAdapter" Version="3.16.1">
@@ -35,6 +36,6 @@
3536
</PackageReference>
3637
</ItemGroup>
3738
<ItemGroup>
38-
<ProjectReference Include="$(SolutionDir)\itext\itext.pdfocr.api\itext.pdfocr.api.csproj" />
39+
<ProjectReference Include="..\..\itext\itext.pdfocr.api\itext.pdfocr.api.csproj" />
3940
</ItemGroup>
4041
</Project>

‎itext.tests/itext.pdfocr.tesseract4.tests/Properties/AssemblyInfo.cs

+3-3
Original file line numberDiff line numberDiff line change
@@ -15,6 +15,6 @@
1515

1616
[assembly: Guid("d6a6ea97-1f23-448f-b700-eff62971d234")]
1717

18-
[assembly: AssemblyVersion("1.0.0.0")]
19-
[assembly: AssemblyFileVersion("1.0.0.0")]
20-
[assembly: AssemblyInformationalVersion("1.0.0")]
18+
[assembly: AssemblyVersion("1.0.1.0")]
19+
[assembly: AssemblyFileVersion("1.0.1.0")]
20+
[assembly: AssemblyInformationalVersion("1.0.1")]

‎itext.tests/itext.pdfocr.tesseract4.tests/itext.pdfocr.tesseract4.tests.csproj

+4-4
Original file line numberDiff line numberDiff line change
@@ -26,8 +26,8 @@
2626
<None Include="itext.snk" />
2727
</ItemGroup>
2828
<ItemGroup>
29-
<PackageReference Include="itext7" Version="7.1.11" />
30-
<PackageReference Include="itext7.pdftest" Version="7.1.11" />
29+
<ProjectReference Include="..\..\..\itextcore\itext\itext.pdftest\itext.pdftest.netstandard.csproj" Condition="Exists('..\..\..\itextcore\itext\itext.pdftest\itext.pdftest.netstandard.csproj')" />
30+
<PackageReference Include="itext7.pdftest" Version="7.1.12" Condition="!Exists('..\..\..\itextcore\itext\itext.pdftest\itext.pdftest.netstandard.csproj')" />
3131
<PackageReference Include="Microsoft.NET.Test.Sdk" Version="16.6.0" />
3232
<PackageReference Include="NUnit" Version="3.12.0" />
3333
<PackageReference Include="NUnit3TestAdapter" Version="3.16.1">
@@ -36,11 +36,11 @@
3636
</PackageReference>
3737
</ItemGroup>
3838
<ItemGroup>
39-
<ProjectReference Include="$(SolutionDir)\itext\itext.pdfocr.tesseract4\itext.pdfocr.tesseract4.csproj" />
39+
<ProjectReference Include="..\..\itext\itext.pdfocr.tesseract4\itext.pdfocr.tesseract4.csproj" />
4040
</ItemGroup>
4141
<ItemGroup>
4242
<Reference Include="Tesseract">
43-
<HintPath>$(SolutionDir)\itext\itext.pdfocr.tesseract4\lib\Tesseract.dll</HintPath>
43+
<HintPath>..\..\itext\itext.pdfocr.tesseract4\lib\Tesseract.dll</HintPath>
4444
</Reference>
4545
</ItemGroup>
4646
</Project>

‎itext.tests/itext.pdfocr.tesseract4.tests/itext/pdfocr/IntegrationTestHelper.cs

+4
Original file line numberDiff line numberDiff line change
@@ -68,6 +68,9 @@ public class IntegrationTestHelper : ExtendedITextTest {
6868
// path to font for hindi
6969
protected internal static readonly String NOTO_SANS_FONT_PATH = TEST_FONTS_DIRECTORY + "NotoSans-Regular.ttf";
7070

71+
// path to font for thai
72+
protected internal static readonly String NOTO_SANS_THAI_FONT_PATH = TEST_FONTS_DIRECTORY + "NotoSansThai-Regular.ttf";
73+
7174
// path to font for japanese
7275
protected internal static readonly String KOSUGI_FONT_PATH = TEST_FONTS_DIRECTORY + "Kosugi-Regular.ttf";
7376

@@ -85,6 +88,7 @@ public class IntegrationTestHelper : ExtendedITextTest {
8588
static IntegrationTestHelper() {
8689
IDictionary<String, String> fontPathToNameMap = new Dictionary<String, String>();
8790
fontPathToNameMap.Put(NOTO_SANS_FONT_PATH, "NotoSans");
91+
fontPathToNameMap.Put(NOTO_SANS_THAI_FONT_PATH, "NotoSansThai");
8892
fontPathToNameMap.Put(KOSUGI_FONT_PATH, "Kosugi");
8993
fontPathToNameMap.Put(NOTO_SANS_SC_FONT_PATH, "NotoSansSC");
9094
fontPathToNameMap.Put(CAIRO_FONT_PATH, "Cairo");

‎itext.tests/itext.pdfocr.tesseract4.tests/itext/pdfocr/events/multithreading/MultiThreadingTest.cs

+7-7
Original file line numberDiff line numberDiff line change
@@ -53,7 +53,7 @@ public static void BeforeClass() {
5353
[NUnit.Framework.SetUp]
5454
public virtual void InitTesseractProperties() {
5555
Tesseract4OcrEngineProperties ocrEngineProperties = new Tesseract4OcrEngineProperties();
56-
ocrEngineProperties.SetPathToTessData(new FileInfo(sourceFolder + "../../tessdata/"));
56+
ocrEngineProperties.SetPathToTessData(new FileInfo(sourceFolder + "../../tessdata"));
5757
tesseractReader.SetTesseract4OcrEngineProperties(ocrEngineProperties);
5858
}
5959

@@ -75,8 +75,6 @@ public virtual void TestEventCountingPdfEvent() {
7575
for (int i = 0; i < n; i++) {
7676
threads[i].Start();
7777
}
78-
// The test will pass in sequential mode, i.e. if the following line is uncommented
79-
//threads[i].join();
8078
for (int i = 0; i < n; i++) {
8179
threads[i].Join();
8280
}
@@ -104,6 +102,10 @@ public virtual void TestEventCountingPdfEvent() {
104102
}
105103
}
106104

105+
private static Thread GetThread(DoImageOcrRunnable runnable) {
106+
return new Thread(new ThreadStart(runnable.Run));
107+
}
108+
107109
public class TestEventCounter : EventCounter {
108110
private IList<IEvent> events = new List<IEvent>();
109111

@@ -117,14 +119,12 @@ public virtual IList<IMetaInfo> GetMetaInfos() {
117119
return metaInfos;
118120
}
119121

122+
[System.Runtime.CompilerServices.MethodImpl(System.Runtime.CompilerServices.MethodImplOptions.Synchronized
123+
)]
120124
protected override void OnEvent(IEvent @event, IMetaInfo metaInfo) {
121125
this.events.Add(@event);
122126
this.metaInfos.Add(metaInfo);
123127
}
124128
}
125-
126-
private static Thread GetThread(DoImageOcrRunnable runnable) {
127-
return new Thread(new ThreadStart(runnable.Run));
128-
}
129129
}
130130
}

‎itext.tests/itext.pdfocr.tesseract4.tests/itext/pdfocr/tessdata/TessDataIntegrationLibTest.cs

+54-4
Original file line numberDiff line numberDiff line change
@@ -24,8 +24,11 @@ You should have received a copy of the GNU Affero General Public License
2424
using System.Collections.Generic;
2525
using System.IO;
2626
using iText.IO.Util;
27+
using iText.Kernel.Colors;
28+
using iText.Kernel.Utils;
2729
using iText.Pdfocr;
2830
using iText.Pdfocr.Tesseract4;
31+
using iText.Test.Attributes;
2932

3033
namespace iText.Pdfocr.Tessdata {
3134
public class TessDataIntegrationLibTest : TessDataIntegrationTest {
@@ -34,8 +37,8 @@ public TessDataIntegrationLibTest()
3437
}
3538

3639
#if !NETSTANDARD1_6
37-
[NUnit.Framework.Timeout(50000)]
38-
#endif
40+
[NUnit.Framework.Timeout(60000)]
41+
#endif // !NETSTANDARD1_6
3942
[NUnit.Framework.Test]
4043
public virtual void TextOutputFromHalftoneFile() {
4144
String imgPath = TEST_IMAGES_DIRECTORY + "halftone.jpg";
@@ -51,8 +54,8 @@ public virtual void TextOutputFromHalftoneFile() {
5154
}
5255

5356
#if !NETSTANDARD1_6
54-
[NUnit.Framework.Timeout(50000)]
55-
#endif
57+
[NUnit.Framework.Timeout(60000)]
58+
#endif // !NETSTANDARD1_6
5659
[NUnit.Framework.Test]
5760
public virtual void HocrOutputFromHalftoneFile() {
5861
String path = TEST_IMAGES_DIRECTORY + "halftone.jpg";
@@ -83,6 +86,53 @@ public virtual void HocrOutputFromHalftoneFile() {
8386
NUnit.Framework.Assert.IsTrue(FindTextInPageData(pageData, 1, expected09));
8487
}
8588

89+
[NUnit.Framework.Test]
90+
public virtual void CompareInvoiceFrontThaiImage() {
91+
String testName = "compareInvoiceFrontThaiImage";
92+
String filename = "invoice_front_thai";
93+
//Tesseract for Java and Tesseract for .NET give different output
94+
//So we cannot use one reference pdf file for them
95+
String expectedPdfPathJava = TEST_DOCUMENTS_DIRECTORY + filename + "_" + testFileTypeName + "_java.pdf";
96+
String expectedPdfPathDotNet = TEST_DOCUMENTS_DIRECTORY + filename + "_" + testFileTypeName + "_dotnet.pdf";
97+
String resultPdfPath = GetTargetDirectory() + filename + "_" + testName + "_" + testFileTypeName + ".pdf";
98+
Tesseract4OcrEngineProperties properties = tesseractReader.GetTesseract4OcrEngineProperties();
99+
properties.SetTextPositioning(TextPositioning.BY_WORDS_AND_LINES);
100+
properties.SetPathToTessData(GetTessDataDirectory());
101+
properties.SetLanguages(JavaUtil.ArraysAsList("tha", "eng"));
102+
tesseractReader.SetTesseract4OcrEngineProperties(properties);
103+
DoOcrAndSavePdfToPath(tesseractReader, TEST_IMAGES_DIRECTORY + filename + ".jpg", resultPdfPath, JavaUtil.ArraysAsList
104+
("tha", "eng"), JavaUtil.ArraysAsList(NOTO_SANS_THAI_FONT_PATH, NOTO_SANS_FONT_PATH), DeviceRgb.RED);
105+
bool javaTest = new CompareTool().CompareByContent(resultPdfPath, expectedPdfPathJava, TEST_DOCUMENTS_DIRECTORY
106+
, "diff_") == null;
107+
bool dotNetTest = new CompareTool().CompareByContent(resultPdfPath, expectedPdfPathDotNet, TEST_DOCUMENTS_DIRECTORY
108+
, "diff_") == null;
109+
NUnit.Framework.Assert.IsTrue(javaTest || dotNetTest);
110+
}
111+
112+
[LogMessage(PdfOcrLogMessageConstant.COULD_NOT_FIND_CORRESPONDING_GLYPH_TO_UNICODE_CHARACTER, Count = 2)]
113+
[NUnit.Framework.Test]
114+
public virtual void CompareThaiTextImage() {
115+
String testName = "compareThaiTextImage";
116+
String filename = "thai_01";
117+
//Tesseract for Java and Tesseract for .NET give different output
118+
//So we cannot use one reference pdf file for them
119+
String expectedPdfPathJava = TEST_DOCUMENTS_DIRECTORY + filename + "_" + testFileTypeName + "_java.pdf";
120+
String expectedPdfPathDotNet = TEST_DOCUMENTS_DIRECTORY + filename + "_" + testFileTypeName + "_dotnet.pdf";
121+
String resultPdfPath = GetTargetDirectory() + filename + "_" + testName + "_" + testFileTypeName + ".pdf";
122+
Tesseract4OcrEngineProperties properties = tesseractReader.GetTesseract4OcrEngineProperties();
123+
properties.SetTextPositioning(TextPositioning.BY_WORDS_AND_LINES);
124+
properties.SetPathToTessData(GetTessDataDirectory());
125+
properties.SetLanguages(JavaUtil.ArraysAsList("tha"));
126+
tesseractReader.SetTesseract4OcrEngineProperties(properties);
127+
DoOcrAndSavePdfToPath(tesseractReader, TEST_IMAGES_DIRECTORY + filename + ".jpg", resultPdfPath, JavaUtil.ArraysAsList
128+
("tha"), JavaUtil.ArraysAsList(NOTO_SANS_THAI_FONT_PATH), DeviceRgb.RED);
129+
bool javaTest = new CompareTool().CompareByContent(resultPdfPath, expectedPdfPathJava, TEST_DOCUMENTS_DIRECTORY
130+
, "diff_") == null;
131+
bool dotNetTest = new CompareTool().CompareByContent(resultPdfPath, expectedPdfPathDotNet, TEST_DOCUMENTS_DIRECTORY
132+
, "diff_") == null;
133+
NUnit.Framework.Assert.IsTrue(javaTest || dotNetTest);
134+
}
135+
86136
/// <summary>Searches for certain text in page data.</summary>
87137
private bool FindTextInPageData(IDictionary<int, IList<TextInfo>> pageData, int page, String textToSearchFor
88138
) {

‎itext.tests/itext.pdfocr.tesseract4.tests/itext/pdfocr/tesseract4/ApiTest.cs

+14
Original file line numberDiff line numberDiff line change
@@ -21,6 +21,7 @@ You should have received a copy of the GNU Affero General Public License
2121
along with this program. If not, see <https://www.gnu.org/licenses/>.
2222
*/
2323
using System;
24+
using System.Collections.Generic;
2425
using System.IO;
2526
using iText.IO.Util;
2627
using iText.Pdfocr;
@@ -126,6 +127,19 @@ public virtual void TestDoTesseractOcrForExecutableForLinux() {
126127
;
127128
}
128129

130+
[LogMessage(Tesseract4LogMessageConstant.CANNOT_PARSE_NODE_BBOX, Count = 4)]
131+
[NUnit.Framework.Test]
132+
public virtual void TestDetectAndFixBrokenBBoxes() {
133+
FileInfo hocrFile = new FileInfo(TEST_DOCUMENTS_DIRECTORY + "broken_bboxes.hocr");
134+
IDictionary<int, IList<TextInfo>> parsedHocr = TesseractHelper.ParseHocrFile(JavaCollectionsUtil.SingletonList
135+
(hocrFile), TextPositioning.BY_WORDS_AND_LINES);
136+
TextInfo textInfo = parsedHocr.Get(1)[1];
137+
NUnit.Framework.Assert.AreEqual(383.0f, (float)textInfo.GetBbox()[0], 0.1);
138+
NUnit.Framework.Assert.AreEqual(101.0f, (float)textInfo.GetBbox()[1], 0.1);
139+
NUnit.Framework.Assert.AreEqual(514.0f, (float)textInfo.GetBbox()[2], 0.1);
140+
NUnit.Framework.Assert.AreEqual(136.0f, (float)textInfo.GetBbox()[3], 0.1);
141+
}
142+
129143
private void TestSettingOsName(String osName) {
130144
String path = TEST_IMAGES_DIRECTORY + "numbers_01.jpg";
131145
FileInfo imgFile = new FileInfo(path);

‎itext.tests/itext.pdfocr.tesseract4.tests/resources/itext/pdfocr/documents/broken_bboxes.hocr

+66
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,66 @@
1+
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
2+
<html>
3+
<head>
4+
<title></title>
5+
<meta http-equiv="Content-Type" content="text/html;charset=utf-8" />
6+
<meta name='ocr-system' content='tesseract'/>
7+
</head>
8+
<body>
9+
<div class='ocr_page' id='page_1' title='image ""; bbox 0 0 1259 318; ppageno 0'>
10+
<div class='ocr_carea' id='block_1_1' title="bbox 97 101 1097 171">
11+
<p class='ocr_par' id='par_1_1' lang='tha' title="bbox 97 101 1099 160">
12+
<span class='ocr_line' id='line_1_1' title="bbox 379 101 979 136; baseline 0.005 -11; x_size 26.279999; x_descenders 5.2799997; x_ascenders 9">
13+
<span class='ocrx_word' id='word_1_1' title='bbox 379 104 383 112; x_wconf 50'>บ</span>
14+
<span class='ocrx_word' id='word_1_2' title='bbox 0 0 1295 318; x_wconf 78'>1</span>
15+
<span class='ocrx_word' id='word_1_3' title='bbox 514 101 539 136; x_wconf 48'>ซ่</span>
16+
<span class='ocrx_word' id='word_1_4' title='bbox 0 0 1295 318; x_wconf 61'>1</span>
17+
<span class='ocrx_word' id='word_1_5' title='bbox 961 117 979 128; x_wconf 20'>ฒ</span>
18+
</span>
19+
<span class='ocr_line' id='line_1_2' title="baseline 0 -11; x_size 33.75; x_descenders 6.75; x_ascenders 11.659091">
20+
<span class='ocrx_word' id='word_1_6' title='x_wconf 96'>ป</span>
21+
<span class='ocrx_word' id='word_1_7' x_wconf 93'>ร</span>
22+
<span class='ocrx_word' id='word_1_8' title='bbox ; x_wconf 93'>ะ</span>
23+
<span class='ocrx_word' id='word_1_9' title='bbox 176 133 212 160; x_wconf 93'>เท</span>
24+
<span class='ocrx_word' id='word_1_10' title='bbox 0 0 1295 318; x_wconf 93'>ศ</span>
25+
<span class='ocrx_word' id='word_1_11' title='bbox 245 113 264 160; x_wconf 93'>ไ</span>
26+
<span class='ocrx_word' id='word_1_12' title='bbox 268 133 292 160; x_wconf 96'>ท</span>
27+
<span class='ocrx_word' id='word_1_13' title='bbox 300 133 317 160; x_wconf 97'>ย</span>
28+
<span class='ocrx_word' id='word_1_14' title='bbox 334 115 356 160; x_wconf 93'>ม</span>
29+
<span class='ocrx_word' id='word_1_15' title='bbox 363 114 376 160; x_wconf 89'>ี</span>
30+
<span class='ocrx_word' id='word_1_16' title='bbox 356 110 411 171; x_wconf 79'>ช็</span>
31+
<span class='ocrx_word' id='word_1_17' title='bbox 394 110 426 171; x_wconf 87'>อ</span>
32+
<span class='ocrx_word' id='word_1_18' title='bbox 417 133 438 160; x_wconf 96'>อ</span>
33+
<span class='ocrx_word' id='word_1_19' title='bbox 445 133 460 160; x_wconf 93'>ย</span>
34+
<span class='ocrx_word' id='word_1_20' title='bbox 468 133 479 160; x_wconf 92'>่</span>
35+
<span class='ocrx_word' id='word_1_21' title='bbox 463 110 494 171; x_wconf 93'>า</span>
36+
<span class='ocrx_word' id='word_1_22' title='bbox 487 133 502 160; x_wconf 96'>ง</span>
37+
<span class='ocrx_word' id='word_1_23' title='bbox 509 116 544 160; x_wconf 92'>เป</span>
38+
<span class='ocrx_word' id='word_1_24' title='bbox 551 133 574 160; x_wconf 93'>็</span>
39+
<span class='ocrx_word' id='word_1_25' title='bbox 554 110 594 171; x_wconf 96'>น</span>
40+
<span class='ocrx_word' id='word_1_26' title='bbox 583 133 607 160; x_wconf 93'>ท</span>
41+
<span class='ocrx_word' id='word_1_27' title='bbox 613 133 627 160; x_wconf 93'>า</span>
42+
<span class='ocrx_word' id='word_1_28' title='bbox 633 133 648 160; x_wconf 96'>ง</span>
43+
<span class='ocrx_word' id='word_1_29' title='bbox 655 133 674 160; x_wconf 93'>ก</span>
44+
<span class='ocrx_word' id='word_1_30' title='bbox 681 133 693 160; x_wconf 93'>า</span>
45+
<span class='ocrx_word' id='word_1_31' title='bbox 701 133 712 160; x_wconf 96'>ร</span>
46+
<span class='ocrx_word' id='word_1_32' title='bbox 699 110 731 171; x_wconf 93'>ว</span>
47+
<span class='ocrx_word' id='word_1_33' title='bbox 725 133 743 160; x_wconf 93'>่</span>
48+
<span class='ocrx_word' id='word_1_34' title='bbox 748 133 761 160; x_wconf 93'>า</span>
49+
<span class='ocrx_word' id='word_1_35' title='bbox 779 133 796 160; x_wconf 93'>ร</span>
50+
<span class='ocrx_word' id='word_1_36' title='bbox 803 133 817 160; x_wconf 93'>า</span>
51+
<span class='ocrx_word' id='word_1_37' title='bbox 822 133 846 160; x_wconf 93'>ช</span>
52+
<span class='ocrx_word' id='word_1_38' title='bbox 850 133 871 160; x_wconf 93'>อ</span>
53+
<span class='ocrx_word' id='word_1_39' title='bbox 877 133 891 160; x_wconf 93'>า</span>
54+
<span class='ocrx_word' id='word_1_40' title='bbox 879 109 926 171; x_wconf 96'>ณา</span>
55+
<span class='ocrx_word' id='word_1_41' title='bbox 933 133 947 160; x_wconf 93'>จ</span>
56+
<span class='ocrx_word' id='word_1_42' title='bbox 953 133 970 160; x_wconf 93'>ั</span>
57+
<span class='ocrx_word' id='word_1_43' title='bbox 977 133 997 160; x_wconf 96'>ก</span>
58+
<span class='ocrx_word' id='word_1_44' title='bbox 1004 133 1021 160; x_wconf 96'>ร</span>
59+
<span class='ocrx_word' id='word_1_45' title='bbox 1027 113 1074 160; x_wconf 96'>ไท</span>
60+
<span class='ocrx_word' id='word_1_46' title='bbox 1082 133 1097 160; x_wconf 96'>ย</span>
61+
</span>
62+
</p>
63+
</div>
64+
</div>
65+
</body>
66+
</html>

‎itext.tests/itext.pdfocr.tesseract4.tests/resources/itext/pdfocr/documents/invoice_front_thai_lib_dotnet.pdf

57.4 KB
Binary file not shown.

‎itext.tests/itext.pdfocr.tesseract4.tests/resources/itext/pdfocr/documents/invoice_front_thai_lib_java.pdf

57.4 KB
Binary file not shown.

‎itext.tests/itext.pdfocr.tesseract4.tests/resources/itext/pdfocr/documents/thai_01_lib_dotnet.pdf

34.5 KB
Binary file not shown.

‎itext.tests/itext.pdfocr.tesseract4.tests/resources/itext/pdfocr/documents/thai_01_lib_java.pdf

34.4 KB
Binary file not shown.

‎itext.tests/itext.pdfocr.tesseract4.tests/resources/itext/pdfocr/fonts/NotoSansThai-Regular.ttf

38.2 KB
Binary file not shown.

‎itext.tests/itext.pdfocr.tesseract4.tests/resources/itext/pdfocr/images/invoice_front_thai.jpg

34.6 KB
Loading

‎itext.tests/itext.pdfocr.tesseract4.tests/resources/itext/pdfocr/images/thai_01.jpg

22.9 KB
Loading

‎itext.tests/itext.pdfocr.tesseract4.tests/resources/itext/pdfocr/tessdata/script/Thai.traineddata

4.05 MB
Binary file not shown.

‎itext.tests/itext.pdfocr.tesseract4.tests/resources/itext/pdfocr/tessdata/tha.traineddata

1.02 MB
Binary file not shown.

‎itext/itext.pdfocr.api/Properties/AssemblyInfo.cs

+3-3
Original file line numberDiff line numberDiff line change
@@ -14,9 +14,9 @@
1414

1515
[assembly: Guid("0c4ceb00-9a56-4547-a925-5974a85a6048")]
1616

17-
[assembly: AssemblyVersion("1.0.0.0")]
18-
[assembly: AssemblyFileVersion("1.0.0.0")]
19-
[assembly: AssemblyInformationalVersion("1.0.0")]
17+
[assembly: AssemblyVersion("1.0.1.0")]
18+
[assembly: AssemblyFileVersion("1.0.1.0")]
19+
[assembly: AssemblyInformationalVersion("1.0.1")]
2020
[assembly: InternalsVisibleTo("itext.pdfocr.api.tests, PublicKey=" +
2121
"00240000048000009400000006020000002400005253413100040000010001008b21ed5b3fc1c1" +
2222
"1996390981fe22bbe71a39a9e11d3c2cefddd6ee92920fa871f9666ae0fa941af0280d0653df04" +

‎itext/itext.pdfocr.api/itext.pdfocr.api.csproj

+6-1
Original file line numberDiff line numberDiff line change
@@ -29,6 +29,11 @@
2929
</EmbeddedResource>
3030
</ItemGroup>
3131
<ItemGroup>
32-
<PackageReference Include="itext7" Version="7.1.11" />
32+
<ProjectReference Include="..\..\..\itextcore\itext\itext.io\itext.io.netstandard.csproj" Condition="Exists('..\..\..\itextcore\itext\itext.io\itext.io.netstandard.csproj')" />
33+
<PackageReference Include="itext7" Version="7.1.12" Condition="!Exists('..\..\..\itextcore\itext\itext.io\itext.io.netstandard.csproj')" />
34+
<ProjectReference Include="..\..\..\itextcore\itext\itext.kernel\itext.kernel.netstandard.csproj" Condition="Exists('..\..\..\itextcore\itext\itext.kernel\itext.kernel.netstandard.csproj')" />
35+
<ProjectReference Include="..\..\..\itextcore\itext\itext.layout\itext.layout.netstandard.csproj" Condition="Exists('..\..\..\itextcore\itext\itext.layout\itext.layout.netstandard.csproj')" />
36+
<ProjectReference Include="..\..\..\itextcore\itext\itext.pdfa\itext.pdfa.netstandard.csproj" Condition="Exists('..\..\..\itextcore\itext\itext.pdfa\itext.pdfa.netstandard.csproj')" />
37+
<ProjectReference Include="..\..\..\itextcore\itext\itext.styledxmlparser\itext.styledxmlparser.netstandard.csproj" Condition="Exists('..\..\..\itextcore\itext\itext.styledxmlparser\itext.styledxmlparser.netstandard.csproj')" />
3338
</ItemGroup>
3439
</Project>

0 commit comments

Comments
 (0)