개정판 79f3f21a
issue #781 text search modify
KCOM/Controls/Sample.xaml | ||
---|---|---|
513 | 513 |
</Grid.ColumnDefinitions> |
514 | 514 |
<Grid.RowDefinitions> |
515 | 515 |
<RowDefinition Height="Auto"/> |
516 |
<RowDefinition Height="Auto"/> |
|
516 | 517 |
<RowDefinition Height="*"/> |
517 | 518 |
</Grid.RowDefinitions> |
518 | 519 |
<Border BorderThickness="0,0,0,1" BorderBrush="#e6e6e6" Background="#f5f5f5"> |
... | ... | |
539 | 540 |
ClearSelectionButtonVisibility="Visible" ClearSelectionButtonContent="Show All" SelectionChanged="commentPage_SelectionChanged"/> |
540 | 541 |
|
541 | 542 |
</Grid> |
543 |
|
|
542 | 544 |
</Border> |
545 |
<Border Grid.Row="1" Background="#f5f5f5" > |
|
546 |
<StackPanel> |
|
547 |
<Border> |
|
548 |
<Grid> |
|
549 |
<Grid.ColumnDefinitions> |
|
550 |
<ColumnDefinition Width="7*"/> |
|
551 |
<ColumnDefinition Width="3*"/> |
|
552 |
</Grid.ColumnDefinitions> |
|
553 |
<TextBox Background="#FFF3F3F3" BorderThickness="0.5" VerticalContentAlignment="Center" x:Name="tbSearch"/> |
|
554 |
|
|
555 |
<Border Background="#FF1258B6" CornerRadius="5" Grid.Column="1" Padding="5" Margin="10"> |
|
556 |
<Button Background="Transparent" Foreground="White" Content="Search" BorderThickness="0" x:Name="btnSearch" Click="btnSearch_Click"/> |
|
557 |
</Border> |
|
543 | 558 |
|
559 |
</Grid> |
|
560 |
</Border> |
|
561 |
</StackPanel> |
|
562 |
</Border> |
|
544 | 563 |
<Border Grid.Row="1" Background="#f5f5f5" Visibility="Collapsed"> |
545 | 564 |
<StackPanel> |
546 | 565 |
<Border> |
... | ... | |
567 | 586 |
</StackPanel> |
568 | 587 |
</Border> |
569 | 588 |
|
570 |
<Border VerticalAlignment="Stretch" Margin="0" Grid.Row="1" BorderThickness="0,0,0,0.5" BorderBrush="#828282" x:Name="gogo">
|
|
589 |
<Border VerticalAlignment="Stretch" Margin="0" Grid.Row="2" BorderThickness="0,0,0,0.5" BorderBrush="#828282" x:Name="gogo">
|
|
571 | 590 |
<telerik:RadListBox telerik:StyleManager.Theme="Office2016" Padding="0" HorizontalAlignment="Stretch" x:Name="gogogo" ScrollViewer.VerticalScrollBarVisibility="Auto" |
572 | 591 |
Background="Transparent" ItemsSource="{Binding MarkupInfoSmallList}" Loaded="gogogo_Loaded"> |
573 | 592 |
<telerik:RadListBox.ItemContainerStyle> |
... | ... | |
587 | 606 |
</Grid.ColumnDefinitions> |
588 | 607 |
|
589 | 608 |
<Image Source="{Binding Data_Type, Converter={StaticResource converterTypeImageConverter}}" Margin="5" Width="28" Height="28"/> |
590 |
<StackPanel Orientation="Vertical" Grid.Column="1" Margin="10" VerticalAlignment="Center"> |
|
609 |
<StackPanel Orientation="Vertical" Grid.Row="0" Grid.Column="1" Margin="10" VerticalAlignment="Center">
|
|
591 | 610 |
<TextBlock Text="{Binding UserName}" FontWeight="DemiBold" Foreground="#3d3d3d"/> |
592 | 611 |
<StackPanel Orientation="Horizontal"> |
593 | 612 |
<TextBlock Text="{Binding PageNumber}"/> |
594 | 613 |
<TextBlock Text=" Page"/> |
595 | 614 |
</StackPanel> |
596 | 615 |
</StackPanel> |
616 |
|
|
597 | 617 |
<Border Background="#FF1258B6" CornerRadius="5" Grid.Column="2" Padding="5" Margin="10"> |
598 | 618 |
<telerik:RadButton Background="Transparent" Foreground="White" Content="Move" BorderThickness="0" Click="RadButton_Click" CommandParameter="{Binding}"/> |
599 | 619 |
</Border> |
KCOM/Controls/Sample.xaml.cs | ||
---|---|---|
676 | 676 |
|
677 | 677 |
private void commentUser_SelectionChanged(object sender, SelectionChangedEventArgs e) |
678 | 678 |
{ |
679 |
tbSearch.Text = string.Empty; |
|
679 | 680 |
if (e.AddedItems.Count > 0) |
680 | 681 |
{ |
681 | 682 |
if (commentUser.Items.Count > 0) |
... | ... | |
923 | 924 |
private void commentType_SelectionChanged(object sender, SelectionChangedEventArgs e) |
924 | 925 |
{ |
925 | 926 |
gogogo.ItemsSource = null; |
927 |
tbSearch.Text = string.Empty; |
|
926 | 928 |
if (e.AddedItems.Count >0) |
927 | 929 |
{ |
928 | 930 |
|
... | ... | |
937 | 939 |
private void commentPage_SelectionChanged(object sender, SelectionChangedEventArgs e) |
938 | 940 |
{ |
939 | 941 |
gogogo.ItemsSource = null; |
942 |
tbSearch.Text = string.Empty; |
|
940 | 943 |
if (e.AddedItems.Count > 0) |
941 | 944 |
{ |
942 | 945 |
gogogo.ItemsSource = MarkupInfoSmallList.Where(d => d.PageNumber == Convert.ToInt32(e.AddedItems[0])).ToList(); |
... | ... | |
951 | 954 |
{ |
952 | 955 |
ViewerDataModel.Instance.SystemMain.dzTopMenu.PanoramaShow(); |
953 | 956 |
} |
957 |
|
|
958 |
private void btnSearch_Click(object sender, RoutedEventArgs e) |
|
959 |
{ |
|
960 |
string search_str = tbSearch.Text; |
|
961 |
var sel_type = commentType.SelectedItem; |
|
962 |
var sel_user = commentUser.SelectedItem; |
|
963 |
var sel_page = commentPage.SelectedItem; |
|
964 |
List<MarkupInfoItemSmall> small_list = new List<MarkupInfoItemSmall>(); |
|
965 |
List<MarkupInfoItemSmall> list = MarkupInfoSmallList; |
|
966 |
if(sel_page !=null) |
|
967 |
{ |
|
968 |
list = list.Where(d => d.PageNumber == Convert.ToInt32(sel_page)).ToList(); |
|
969 |
} |
|
970 |
if(sel_type !=null) |
|
971 |
{ |
|
972 |
list = list.Where(d => d.Data_Type == Convert.ToInt32(sel_type)).ToList(); |
|
973 |
} |
|
974 |
if (sel_user != null) |
|
975 |
{ |
|
976 |
list = list.Where(d => d.UserID == (sel_user as MarkupInfoItem).UserID).ToList(); |
|
977 |
} |
|
978 |
foreach (var item in list) |
|
979 |
{ |
|
980 |
var data = MarkupToPDF.Serialize.Core.JsonSerializerHelper.UnCompressString(item.Data.ToString()); |
|
981 |
|
|
982 |
switch (Enum.Parse(typeof(MarkupToPDF.Controls.Common.ControlType), item.Data_Type.ToString())) |
|
983 |
{ |
|
984 |
case MarkupToPDF.Controls.Common.ControlType.TextControl: |
|
985 |
case MarkupToPDF.Controls.Common.ControlType.TextBorder: |
|
986 |
case MarkupToPDF.Controls.Common.ControlType.TextCloud: |
|
987 |
{ |
|
988 |
MarkupToPDF.Serialize.S_Control.S_TextControl instance = MarkupToPDF.Serialize.Core.JsonSerializerHelper.JsonDeserialize<MarkupToPDF.Serialize.S_Control.S_TextControl>(data); |
|
989 |
if (instance.Text.Contains(search_str)) |
|
990 |
{ |
|
991 |
small_list.Add(item); |
|
992 |
} |
|
993 |
} |
|
994 |
break; |
|
995 |
case MarkupToPDF.Controls.Common.ControlType.ArrowTextBorderControl: |
|
996 |
case MarkupToPDF.Controls.Common.ControlType.ArrowTextCloudControl: |
|
997 |
case MarkupToPDF.Controls.Common.ControlType.ArrowTextControl: |
|
998 |
case MarkupToPDF.Controls.Common.ControlType.ArrowTransTextBorderControl: |
|
999 |
case MarkupToPDF.Controls.Common.ControlType.ArrowTransTextCloudControl: |
|
1000 |
case MarkupToPDF.Controls.Common.ControlType.ArrowTransTextControl: |
|
1001 |
{ |
|
1002 |
MarkupToPDF.Serialize.S_Control.S_ArrowTextControl instance = MarkupToPDF.Serialize.Core.JsonSerializerHelper.JsonDeserialize<MarkupToPDF.Serialize.S_Control.S_ArrowTextControl>(data); |
|
1003 |
if (instance.ArrowText.Contains(search_str)) |
|
1004 |
{ |
|
1005 |
small_list.Add(item); |
|
1006 |
} |
|
1007 |
} |
|
1008 |
break; |
|
1009 |
|
|
1010 |
} |
|
1011 |
|
|
1012 |
} |
|
1013 |
|
|
1014 |
gogogo.ItemsSource = null; |
|
1015 |
gogogo.ItemsSource = small_list.OrderBy(d => d.PageNumber).ToList(); |
|
1016 |
tbSearch.Text = string.Empty; |
|
1017 |
} |
|
954 | 1018 |
} |
955 | 1019 |
} |
KCOM/Controls/SearchPanel.xaml | ||
---|---|---|
23 | 23 |
</Grid> |
24 | 24 |
<GroupBox Header="Option List"> |
25 | 25 |
<StackPanel Margin="1"> |
26 |
<CheckBox Content="Current page only" Margin="3" x:Name="chkCurrentPageOnly"/> |
|
26 |
<CheckBox Content="Current page only" Margin="3" x:Name="chkCurrentPageOnly" IsChecked="True"/> |
|
27 |
<CheckBox Content="Comment Include" Margin="3" x:Name="chkCommentinclude" IsChecked="True"/> |
|
27 | 28 |
</StackPanel> |
28 | 29 |
</GroupBox> |
29 | 30 |
<GroupBox Header="Search Mode"> |
KCOM/Controls/SearchPanel.xaml.cs | ||
---|---|---|
31 | 31 |
string RegistrationKey = "193B-FD48-42F4-68E6-2D35-4C94-D07"; |
32 | 32 |
string RegistrationName = "license@doftech.co.kr"; |
33 | 33 |
Bytescout.PDFExtractor.TextExtractor extractor; |
34 |
|
|
34 |
Bytescout.PDFExtractor.OCRAnalyzer ocrAnalyzer; |
|
35 | 35 |
public SearchPanel() |
36 | 36 |
{ |
37 |
//InitializeComponent(); |
|
38 |
this.Loaded += SearchPanel_Loaded; |
|
37 |
InitializeComponent(); |
|
38 |
LibInit(); |
|
39 |
//this.Loaded += SearchPanel_Loaded; |
|
40 |
btnSearch.Click += BtnSearch_Click; |
|
41 |
btnSearchPDFDownload.Click += BtnSearchPDFDownload_Click; |
|
42 |
SearchSet = new System.Collections.ObjectModel.ObservableCollection<SearchText>(); |
|
39 | 43 |
|
44 |
tbSearch.KeyDown += tbSearch_KeyDown; |
|
45 |
this.DataContext = this; |
|
46 |
|
|
47 |
|
|
48 |
|
|
49 |
/* |
|
50 |
if (Common.ViewerDataModel.Instance.searchPDF ==null) |
|
51 |
{ |
|
52 |
|
|
53 |
} |
|
54 |
else |
|
55 |
{ |
|
56 |
border_Overlap.Visibility = Visibility.Collapsed; |
|
57 |
tbSearch.Focus(); |
|
58 |
|
|
59 |
} |
|
60 |
*/ |
|
61 |
|
|
62 |
if (Common.ViewerDataModel.Instance.searchPDF != null) |
|
63 |
{ |
|
64 |
border_Overlap.Visibility = Visibility.Collapsed; |
|
65 |
tbSearch.Focus(); |
|
66 |
} |
|
40 | 67 |
} |
41 | 68 |
|
42 | 69 |
private void tbSearch_KeyDown(object sender, KeyEventArgs e) |
... | ... | |
46 | 73 |
SearchMethod(); |
47 | 74 |
} |
48 | 75 |
} |
76 |
private void LibInit() |
|
77 |
{ |
|
78 |
extractor = new Bytescout.PDFExtractor.TextExtractor(RegistrationName, RegistrationKey); |
|
79 |
ocrAnalyzer = new Bytescout.PDFExtractor.OCRAnalyzer(RegistrationName, RegistrationKey); |
|
80 |
extractor.OCRMode = Bytescout.PDFExtractor.OCRMode.Auto; |
|
81 |
extractor.OCRLanguage = "eng"; |
|
82 |
extractor.OCRLanguageDataFolder = System.AppDomain.CurrentDomain.BaseDirectory + "\\tessdata\\"; |
|
83 |
extractor.OCRResolution = 300; |
|
84 |
|
|
85 |
ocrAnalyzer.OCRLanguage = "eng"; |
|
86 |
ocrAnalyzer.OCRLanguageDataFolder = System.AppDomain.CurrentDomain.BaseDirectory + "\\tessdata\\"; |
|
49 | 87 |
|
88 |
} |
|
50 | 89 |
private void SearchPanel_Loaded(object sender, RoutedEventArgs e) |
51 | 90 |
{ |
52 | 91 |
//측정 |
... | ... | |
54 | 93 |
//sw.Start(); |
55 | 94 |
InitializeComponent(); |
56 | 95 |
//System.Diagnostics.Debug.WriteLine("SearchPanel() : " + sw.ElapsedMilliseconds.ToString() + "ms"); |
57 |
|
|
96 |
|
|
58 | 97 |
btnSearch.Click += BtnSearch_Click; |
59 | 98 |
btnSearchPDFDownload.Click += BtnSearchPDFDownload_Click; |
60 | 99 |
SearchSet = new System.Collections.ObjectModel.ObservableCollection<SearchText>(); |
61 | 100 |
extractor = new Bytescout.PDFExtractor.TextExtractor(RegistrationName, RegistrationKey); |
62 | 101 |
tbSearch.KeyDown += tbSearch_KeyDown; |
63 | 102 |
this.DataContext = this; |
64 |
|
|
103 |
|
|
65 | 104 |
/* |
66 | 105 |
if (Common.ViewerDataModel.Instance.searchPDF ==null) |
67 | 106 |
{ |
... | ... | |
110 | 149 |
{ |
111 | 150 |
SearchMethod(); |
112 | 151 |
} |
113 |
|
|
152 |
|
|
114 | 153 |
private void SearchMethod() |
115 | 154 |
{ |
116 |
extractor.LoadDocumentFromFile(Common.ViewerDataModel.Instance.searchPDF.FullName); |
|
155 |
|
|
117 | 156 |
SearchSet.Clear(); |
118 | 157 |
string searchString = tbSearch.Text; |
119 |
int pageCount = extractor.GetPageCount(); |
|
158 |
extractor.LoadDocumentFromFile(Common.ViewerDataModel.Instance.searchPDF.FullName); |
|
159 |
ocrAnalyzer.LoadDocumentFromFile(Common.ViewerDataModel.Instance.searchPDF.FullName); |
|
120 | 160 |
|
121 | 161 |
if (chkCurrentPageOnly.IsChecked.Value) |
122 | 162 |
{ |
123 | 163 |
var currentPage = Common.ViewerDataModel.Instance.SystemMain.dzMainMenu.pageNavigator.CurrentPage.PageNumber - 1; |
164 |
|
|
165 |
Bytescout.PDFExtractor.OCRAnalysisResults analysisResults = ocrAnalyzer.AnalyzeByOCRConfidence(currentPage); |
|
166 |
ocrAnalyzer.ApplyResults(analysisResults, extractor); |
|
167 |
|
|
124 | 168 |
if (extractor.Find(currentPage, searchString, false)) |
125 | 169 |
do |
126 | 170 |
{ |
... | ... | |
130 | 174 |
} |
131 | 175 |
else |
132 | 176 |
{ |
177 |
int pageCount = extractor.GetPageCount(); |
|
133 | 178 |
for (int i = 0; i < pageCount; i++) |
134 | 179 |
{ |
180 |
Bytescout.PDFExtractor.OCRAnalysisResults analysisResults = ocrAnalyzer.AnalyzeByOCRConfidence(i); |
|
181 |
ocrAnalyzer.ApplyResults(analysisResults, extractor); |
|
135 | 182 |
if (extractor.Find(i, searchString, false)) |
136 | 183 |
do |
137 | 184 |
{ |
KCOM/KCOM.csproj | ||
---|---|---|
68 | 68 |
<ApplicationManifest>Properties\app.manifest</ApplicationManifest> |
69 | 69 |
</PropertyGroup> |
70 | 70 |
<ItemGroup> |
71 |
<Reference Include="Bytescout.PDFExtractor, Version=9.1.0.3170, Culture=neutral, PublicKeyToken=f7dd1bd9d40a50eb, processorArchitecture=MSIL" /> |
|
72 |
<Reference Include="Bytescout.PDFExtractor.OCRExtension, Version=9.0.0.3095, Culture=neutral, PublicKeyToken=f7dd1bd9d40a50eb, processorArchitecture=MSIL"> |
|
71 |
<Reference Include="Bytescout.PDFExtractor, Version=9.2.0.3293, Culture=neutral, PublicKeyToken=f7dd1bd9d40a50eb, processorArchitecture=MSIL"> |
|
73 | 72 |
<SpecificVersion>False</SpecificVersion> |
74 |
<HintPath>bin\x64\Debug\Bytescout.PDFExtractor.OCRExtension.dll</HintPath> |
|
73 |
<HintPath>..\packages\PDFExtractorSDK\FULL\net4.00\Bytescout.PDFExtractor.dll</HintPath> |
|
74 |
</Reference> |
|
75 |
<Reference Include="Bytescout.PDFExtractor.OCRExtension, Version=9.2.0.3293, Culture=neutral, PublicKeyToken=f7dd1bd9d40a50eb, processorArchitecture=MSIL"> |
|
76 |
<SpecificVersion>False</SpecificVersion> |
|
77 |
<HintPath>..\packages\PDFExtractorSDK\FULL\net4.00\Bytescout.PDFExtractor.OCRExtension.dll</HintPath> |
|
75 | 78 |
</Reference> |
76 | 79 |
<Reference Include="EntityFramework, Version=4.3.1.0, Culture=neutral, PublicKeyToken=b77a5c561934e089, processorArchitecture=MSIL"> |
77 | 80 |
<HintPath>..\packages\EntityFramework.4.3.1\lib\net40\EntityFramework.dll</HintPath> |
... | ... | |
508 | 511 |
<Generator>SettingsSingleFileGenerator</Generator> |
509 | 512 |
<LastGenOutput>Settings.Designer.cs</LastGenOutput> |
510 | 513 |
</None> |
514 |
<None Include="tessdata\deu.traineddata"> |
|
515 |
<CopyToOutputDirectory>Always</CopyToOutputDirectory> |
|
516 |
</None> |
|
517 |
<None Include="tessdata\eng.traineddata"> |
|
518 |
<CopyToOutputDirectory>Always</CopyToOutputDirectory> |
|
519 |
</None> |
|
520 |
<None Include="tessdata\fra.traineddata"> |
|
521 |
<CopyToOutputDirectory>Always</CopyToOutputDirectory> |
|
522 |
</None> |
|
523 |
<None Include="tessdata\spa.traineddata"> |
|
524 |
<CopyToOutputDirectory>Always</CopyToOutputDirectory> |
|
525 |
</None> |
|
511 | 526 |
<None Include="Web References\Get_FinalImage\Get_PdfImage.wsdl" /> |
512 | 527 |
<None Include="Web References\Get_FinalImage\Reference.map"> |
513 | 528 |
<Generator>MSDiscoCodeGenerator</Generator> |
packages/PDFExtractorSDK/FULL/ActiveX/InstallAsActiveX.bat | ||
---|---|---|
1 |
@echo off |
|
2 |
|
|
3 |
REM -------------------------------------------------------------------------------------- |
|
4 |
REM - This batch registers assemblies as ActiveX object using .NET 4.0 or 2.0 - |
|
5 |
REM - for x86, x64 and x86 emulation modes. - |
|
6 |
REM - On Windows Vista and later this batch should be ran in "As Administrator" mode. - |
|
7 |
REM -------------------------------------------------------------------------------------- |
|
8 |
|
|
9 |
REM ! If you are getting error "System.IO.FileLoadException: Could not load file or |
|
10 |
REM ! assembly ‘file:///<filename>’ or one of its dependencies. Operation is not supported. |
|
11 |
REM ! (Exception from HRESULT: 0x80131515)." when executing this file, you have doubtless |
|
12 |
REM ! used Windows Explorer to extract files from the zip package and all files have been |
|
13 |
REM ! marked as blocked by security reason. |
|
14 |
REM ! Solution: |
|
15 |
REM ! - Use other application to unzip the package. |
|
16 |
REM ! or |
|
17 |
REM ! - Open properties of each extracted file, click `Unblock` and "Apply". |
|
18 |
|
|
19 |
|
|
20 |
REM change current directory (required for Vista and higher) |
|
21 |
@setlocal enableextensions |
|
22 |
@cd /d "%~dp0" |
|
23 |
|
|
24 |
SET DLLFILE=Bytescout.PDFExtractor.dll |
|
25 |
SET DLLFILE2=Bytescout.PDFExtractor.OCRExtension.dll |
|
26 |
SET TLBFILE=Bytescout.PDFExtractor.tlb |
|
27 |
|
|
28 |
SET ERROR=0 |
|
29 |
|
|
30 |
echo ------------ x86 Windows installation ------------------------ |
|
31 |
|
|
32 |
IF NOT EXIST "%systemroot%\SYSWOW64\" ( |
|
33 |
|
|
34 |
REM pure x86 mode |
|
35 |
|
|
36 |
ECHO. |
|
37 |
ECHO Check if .NET 4.0 is available |
|
38 |
ECHO. |
|
39 |
|
|
40 |
IF EXIST "%windir%\Microsoft.NET\Framework\v4.0.30319\regasm.exe" ( |
|
41 |
|
|
42 |
ECHO. |
|
43 |
ECHO Copying .NET 4.0 DLL and TLB files to 'System32' |
|
44 |
ECHO. |
|
45 |
|
|
46 |
copy "..\net4.00\%DLLFILE%" "%windir%\System32\%DLLFILE%" |
|
47 |
copy "..\net4.00\%DLLFILE2%" "%windir%\System32\%DLLFILE2%" |
|
48 |
copy "..\net4.00\%TLBFILE%" "%windir%\System32\%TLBFILE%" |
|
49 |
|
|
50 |
ECHO. |
|
51 |
ECHO Registering .NET 4.0 assembly as ActiveX |
|
52 |
ECHO. |
|
53 |
"%windir%\Microsoft.NET\Framework\v4.0.30319\regasm.exe" "%windir%\System32\%DLLFILE%" /tlb:"%windir%\System32\%TLBFILE%" /codebase |
|
54 |
|
|
55 |
REM Else try installing with .NET 2.0 |
|
56 |
) ELSE ( |
|
57 |
|
|
58 |
ECHO. |
|
59 |
ECHO Check if .NET 2.0 is available |
|
60 |
ECHO. |
|
61 |
|
|
62 |
IF EXIST "%windir%\Microsoft.NET\Framework\v2.0.50727\regasm.exe" ( |
|
63 |
|
|
64 |
ECHO. |
|
65 |
ECHO Copying DLL and TLB files to 'System32' |
|
66 |
ECHO. |
|
67 |
|
|
68 |
copy "..\net2.00\%DLLFILE%" "%windir%\System32\%DLLFILE%" |
|
69 |
copy "..\net2.00\%DLLFILE2%" "%windir%\System32\%DLLFILE2%" |
|
70 |
copy "..\net2.00\%TLBFILE%" "%windir%\System32\%TLBFILE%" |
|
71 |
|
|
72 |
ECHO. |
|
73 |
ECHO Register .NET 2.0 assembly as ActiveX |
|
74 |
ECHO. |
|
75 |
"%windir%\Microsoft.NET\Framework\v2.0.50727\regasm.exe" "%windir%\System32\%DLLFILE%" /tlb:"%windir%\System32\%TLBFILE%" /codebase |
|
76 |
|
|
77 |
REM Display error message |
|
78 |
) ELSE ( |
|
79 |
|
|
80 |
ECHO. |
|
81 |
ECHO ERROR: Could not find .NET 2.0 or .NET 4.0 framework installed. |
|
82 |
ECHO. |
|
83 |
|
|
84 |
ERROR = -1 |
|
85 |
GOTO :SHOWERROR |
|
86 |
) |
|
87 |
|
|
88 |
) |
|
89 |
|
|
90 |
) |
|
91 |
|
|
92 |
|
|
93 |
echo ------------ x64 Windows installation ------------------------ |
|
94 |
|
|
95 |
REM Check if we are on Windows x64 |
|
96 |
IF EXIST "%systemroot%\SYSWOW64\" ( |
|
97 |
|
|
98 |
ECHO. |
|
99 |
ECHO x64 native mode and x86 emulation modes installations |
|
100 |
ECHO. |
|
101 |
|
|
102 |
REM --- x86 on x64 |
|
103 |
ECHO. |
|
104 |
ECHO 1. x86 emulation mode on x64 |
|
105 |
ECHO. |
|
106 |
|
|
107 |
ECHO. |
|
108 |
ECHO Check if .NET 4.0 for x86 is installed |
|
109 |
ECHO. |
|
110 |
|
|
111 |
IF EXIST "%windir%\Microsoft.NET\Framework\v4.0.30319\regasm.exe" ( |
|
112 |
|
|
113 |
ECHO. |
|
114 |
ECHO Copying .NET 4.0 DLL and TLB files to /System32/ |
|
115 |
ECHO. |
|
116 |
|
|
117 |
copy "..\net4.00\%DLLFILE%" "%systemroot%\SYSWOW64\%DLLFILE%" |
|
118 |
copy "..\net4.00\%DLLFILE2%" "%systemroot%\SYSWOW64\%DLLFILE2%" |
|
119 |
copy "..\net4.00\%TLBFILE%" "%systemroot%\SYSWOW64\%TLBFILE%" |
|
120 |
|
|
121 |
ECHO. |
|
122 |
ECHO Registering .NET 4.0 assembly as ActiveX in .NET x86 on x64 |
|
123 |
ECHO. |
|
124 |
"%windir%\Microsoft.NET\Framework\v4.0.30319\regasm.exe" "%systemroot%\SYSWOW64\%DLLFILE%" /tlb:"%systemroot%\SYSWOW64\%TLBFILE%" /codebase |
|
125 |
|
|
126 |
) ELSE ( |
|
127 |
|
|
128 |
ECHO. |
|
129 |
ECHO Check if .NET 2.0 for x86 is installed |
|
130 |
ECHO. |
|
131 |
|
|
132 |
IF EXIST "%windir%\Microsoft.NET\Framework\v2.0.50727\regasm.exe" ( |
|
133 |
|
|
134 |
ECHO. |
|
135 |
ECHO Copying .NET 2.0 DLL and TLB files to /System32/ |
|
136 |
ECHO. |
|
137 |
|
|
138 |
copy "..\net2.00\%DLLFILE%" "%systemroot%\SYSWOW64\%DLLFILE%" |
|
139 |
copy "..\net2.00\%DLLFILE2%" "%systemroot%\SYSWOW64\%DLLFILE2%" |
|
140 |
copy "..\net2.00\%TLBFILE%" "%systemroot%\SYSWOW64\%TLBFILE%" |
|
141 |
|
|
142 |
ECHO. |
|
143 |
ECHO Registering .NET 2.0 assembly as ActiveX in .NET x86 on x64 |
|
144 |
ECHO. |
|
145 |
"%windir%\Microsoft.NET\Framework\v2.0.50727\regasm.exe" "%systemroot%\SYSWOW64\%DLLFILE%" /tlb:"%systemroot%\SYSWOW64\%TLBFILE%" /codebase |
|
146 |
|
|
147 |
REM Display error message |
|
148 |
) ELSE ( |
|
149 |
|
|
150 |
ECHO. |
|
151 |
ECHO ERROR: Could not find .NET 2.0 or .NET 4.0 framework installed. |
|
152 |
ECHO. |
|
153 |
|
|
154 |
ERROR = -2 |
|
155 |
GOTO :SHOWERROR |
|
156 |
|
|
157 |
) |
|
158 |
) |
|
159 |
|
|
160 |
|
|
161 |
REM --- x64 mode |
|
162 |
|
|
163 |
ECHO. |
|
164 |
ECHO 2. x64 native mode on x64 |
|
165 |
ECHO. |
|
166 |
|
|
167 |
IF EXIST "%windir%\Microsoft.NET\Framework64\v4.0.30319\regasm.exe" ( |
|
168 |
|
|
169 |
ECHO. |
|
170 |
ECHO Copying .NET 4.0 DLL and TLB files to 'System32' |
|
171 |
ECHO. |
|
172 |
|
|
173 |
IF EXIST "%systemroot%\sysnative\cmd.exe" ( |
|
174 |
|
|
175 |
REM We call cmd.exe and regsvr32.exe from "sysnative" folder (special "alias" available when running x86 batch on x64). |
|
176 |
REM Although we call from "sysnative" folder, we should pass "system32" in command line parameters. |
|
177 |
|
|
178 |
ECHO Copying sysnative\%DLLFILE%" |
|
179 |
"%systemroot%\sysnative\cmd.exe" /c copy "..\net4.00\%DLLFILE%" "%systemroot%\system32\%DLLFILE%" |
|
180 |
ECHO copying sysnative\%DLLFILE2%" |
|
181 |
"%systemroot%\sysnative\cmd.exe" /c copy "..\net4.00\%DLLFILE2%" "%systemroot%\system32\%DLLFILE2%" |
|
182 |
ECHO Copying sysnative\%TLBFILE%" |
|
183 |
"%systemroot%\sysnative\cmd.exe" /c copy "..\net4.00\%TLBFILE%" "%systemroot%\system32\%TLBFILE%" |
|
184 |
|
|
185 |
ECHO. |
|
186 |
ECHO Registering .NET 4.0 assembly as ActiveX in .NET x64 |
|
187 |
ECHO. |
|
188 |
"%windir%\Microsoft.NET\Framework64\v4.0.30319\regasm.exe" "%windir%\System32\%DLLFILE%" /tlb:"%windir%\System32\%TLBFILE%" /codebase |
|
189 |
|
|
190 |
) ELSE ( |
|
191 |
|
|
192 |
ECHO Copying system32\%DLLFILE%" |
|
193 |
copy "..\net4.00\%DLLFILE%" "%windir%\System32\%DLLFILE%" |
|
194 |
ECHO copying system32\%DLLFILE2%" |
|
195 |
copy "..\net4.00\%DLLFILE2%" "%windir%\System32\%DLLFILE2%" |
|
196 |
ECHO Copying system32\%TLBFILE%" |
|
197 |
copy "..\net4.00\%TLBFILE%" "%windir%\System32\%TLBFILE%" |
|
198 |
|
|
199 |
ECHO. |
|
200 |
ECHO Registering .NET 4.0 assembly as ActiveX in .NET x64 |
|
201 |
ECHO. |
|
202 |
"%windir%\Microsoft.NET\Framework64\v4.0.30319\regasm.exe" "%windir%\System32\%DLLFILE%" /tlb:"%windir%\System32\%TLBFILE%" /codebase |
|
203 |
|
|
204 |
) |
|
205 |
|
|
206 |
) ELSE ( |
|
207 |
|
|
208 |
IF EXIST "%windir%\Microsoft.NET\Framework64\v2.0.50727\regasm.exe" ( |
|
209 |
|
|
210 |
IF EXIST "%systemroot%\sysnative\cmd.exe" ( |
|
211 |
|
|
212 |
REM We call cmd.exe and regsvr32.exe from "sysnative" folder (special "alias" available when running x86 batch on x64). |
|
213 |
REM Although we call from "sysnative" folder, we should pass "system32" in command line parameters. |
|
214 |
|
|
215 |
ECHO Copying sysnative\%DLLFILE%" |
|
216 |
"%systemroot%\sysnative\cmd.exe" /c copy "..\net2.00\%DLLFILE%" "%systemroot%\system32\%DLLFILE%" |
|
217 |
ECHO copying sysnative\%DLLFILE2%" |
|
218 |
"%systemroot%\sysnative\cmd.exe" /c copy "..\net2.00\%DLLFILE2%" "%systemroot%\system32\%DLLFILE2%" |
|
219 |
ECHO Copying sysnative\%TLBFILE%" |
|
220 |
"%systemroot%\sysnative\cmd.exe" /c copy "..\net2.00\%TLBFILE%" "%systemroot%\system32\%TLBFILE%" |
|
221 |
|
|
222 |
ECHO. |
|
223 |
ECHO Registering .NET 2.0 assembly as ActiveX in .NET x64 |
|
224 |
ECHO. |
|
225 |
"%windir%\Microsoft.NET\Framework64\v2.0.50727\regasm.exe" "%windir%\system32\%DLLFILE%" /tlb:"%windir%\system32\%TLBFILE%" /codebase |
|
226 |
|
|
227 |
) ELSE ( |
|
228 |
|
|
229 |
ECHO Copying system32\%DLLFILE%" |
|
230 |
copy "..\net2.00\%DLLFILE%" "%windir%\System32\%DLLFILE%" |
|
231 |
ECHO copying system32\%DLLFILE2%" |
|
232 |
copy "..\net2.00\%DLLFILE2%" "%windir%\System32\%DLLFILE2%" |
|
233 |
ECHO Copying system32\%TLBFILE%" |
|
234 |
copy "..\net2.00\%TLBFILE%" "%windir%\System32\%TLBFILE%" |
|
235 |
|
|
236 |
ECHO. |
|
237 |
ECHO Registering .NET 2.0 assembly as ActiveX in .NET x64 |
|
238 |
ECHO. |
|
239 |
"%windir%\Microsoft.NET\Framework64\v2.0.50727\regasm.exe" "%windir%\System32\%DLLFILE%" /tlb:"%windir%\System32\%TLBFILE%" /codebase |
|
240 |
|
|
241 |
) |
|
242 |
|
|
243 |
REM Display error message |
|
244 |
) ELSE ( |
|
245 |
|
|
246 |
ECHO. |
|
247 |
ECHO ERROR: Could not find .NET 2.0 or .NET 4.0 framework installed. |
|
248 |
ECHO. |
|
249 |
|
|
250 |
ERROR = -3 |
|
251 |
GOTO :ERROR |
|
252 |
|
|
253 |
) |
|
254 |
|
|
255 |
) |
|
256 |
|
|
257 |
) |
|
258 |
|
|
259 |
|
|
260 |
if %ERROR% EQU 0 goto :EOF |
|
261 |
|
|
262 |
:SHOWERROR |
|
263 |
|
|
264 |
echo . |
|
265 |
echo Could not register assemblies as ActiveX: %ERROR% |
|
266 |
echo . |
|
267 |
|
|
268 |
REM Exit %ERROR% |
|
269 |
|
|
270 |
:EOF |
packages/PDFExtractorSDK/FULL/ActiveX/UninstallAsActiveX.bat | ||
---|---|---|
1 |
@echo off |
|
2 |
|
|
3 |
REM -------------------------------------------------------------------------------------- |
|
4 |
REM - This batch uninstalls assemblies as ActiveX object using .NET 2.0 or 4.0 - |
|
5 |
REM - for x86, x64 and x86 emulation modes. - |
|
6 |
REM - On Windows Vista and later this batch should be ran in "As Administrator" mode. - |
|
7 |
REM -------------------------------------------------------------------------------------- |
|
8 |
|
|
9 |
SET DLLFILE=Bytescout.PDFExtractor.dll |
|
10 |
SET DLLFILE2=Bytescout.PDFExtractor.OCRExtension.dll |
|
11 |
SET TLBFILE=Bytescout.PDFExtractor.tlb |
|
12 |
|
|
13 |
SET ERROR=0 |
|
14 |
|
|
15 |
|
|
16 |
REM ------------ x86 Windows deinstallation ------------------------ |
|
17 |
|
|
18 |
IF NOT EXIST "%systemroot%\SYSWOW64\" ( |
|
19 |
|
|
20 |
IF NOT "%DLLFILE%"=="" IF NOT "%DLLFILE2%"=="" IF NOT "%TLBFILE%"=="" IF EXIST "%windir%\system32\%DLLFILE%" ( |
|
21 |
|
|
22 |
REM Unregister assembly as ActiveX |
|
23 |
IF EXIST "%windir%\Microsoft.NET\Framework\v4.0.30319\regasm.exe" "%windir%\Microsoft.NET\Framework\v4.0.30319\regasm.exe" "%windir%\System32\%DLLFILE%" /tlb:"%windir%\System32\%TLBFILE%" /unregister |
|
24 |
IF EXIST "%windir%\Microsoft.NET\Framework\v2.0.50727\regasm.exe" "%windir%\Microsoft.NET\Framework\v2.0.50727\regasm.exe" "%windir%\System32\%DLLFILE%" /tlb:"%windir%\System32\%TLBFILE%" /unregister |
|
25 |
|
|
26 |
REM Delete files |
|
27 |
DEL "%windir%\System32\%DLLFILE%" |
|
28 |
DEL "%windir%\System32\%DLLFILE2%" |
|
29 |
DEL "%windir%\System32\%TLBFILE%" |
|
30 |
|
|
31 |
) ELSE ( |
|
32 |
|
|
33 |
ECHO. |
|
34 |
ECHO %DLLFILE% not found so nothing to uninstall |
|
35 |
ECHO. |
|
36 |
) |
|
37 |
|
|
38 |
) ELSE ( |
|
39 |
|
|
40 |
REM ------------ x64 Windows deinstallation ------------------------ |
|
41 |
|
|
42 |
REM check x86 emulation mode files |
|
43 |
|
|
44 |
IF NOT "%DLLFILE%"=="" IF NOT "%DLLFILE2%"=="" IF NOT "%TLBFILE%"=="" IF EXIST "%windir%\SYSWOW64\%DLLFILE%" ( |
|
45 |
|
|
46 |
echo. |
|
47 |
echo Unregistering assembly as ActiveX from x86 emulation mode |
|
48 |
echo. |
|
49 |
IF EXIST "%windir%\Microsoft.NET\Framework\v4.0.30319\regasm.exe" "%windir%\Microsoft.NET\Framework\v4.0.30319\regasm.exe" "%windir%\SYSWOW64\%DLLFILE%" /tlb:"%windir%\SYSWOW64\%TLBFILE%" /unregister |
|
50 |
IF EXIST "%windir%\Microsoft.NET\Framework\v2.0.50727\regasm.exe" "%windir%\Microsoft.NET\Framework\v2.0.50727\regasm.exe" "%windir%\SYSWOW64\%DLLFILE%" /tlb:"%windir%\SYSWOW64\%TLBFILE%" /unregister |
|
51 |
|
|
52 |
echo. |
|
53 |
echo Delete files from x86 emulation mode |
|
54 |
echo. |
|
55 |
DEL "%windir%\SYSWOW64\%DLLFILE%" |
|
56 |
DEL "%windir%\SYSWOW64\%DLLFILE2%" |
|
57 |
DEL "%windir%\SYSWOW64\%TLBFILE%" |
|
58 |
|
|
59 |
) ELSE ( |
|
60 |
|
|
61 |
ECHO. |
|
62 |
ECHO x86 emulation mode on x64: %DLLFILE% not found so nothing to uninstall |
|
63 |
ECHO. |
|
64 |
) |
|
65 |
|
|
66 |
IF NOT "%DLLFILE%"=="" IF NOT "%DLLFILE2%"=="" IF NOT "%TLBFILE%"=="" ( |
|
67 |
|
|
68 |
REM case #1 (this batch runs from x86 console so should use "sysnative" alias to access x64 folders) |
|
69 |
IF EXIST "%windir%\sysnative\%DLLFILE%" ( |
|
70 |
|
|
71 |
echo. |
|
72 |
echo Unregistering .NET 4.0 version if registered |
|
73 |
echo. |
|
74 |
IF EXIST "%windir%\Microsoft.NET\Framework64\v4.0.30319\regasm.exe" "%windir%\Microsoft.NET\Framework64\v4.0.30319\regasm.exe" "%windir%\system32\%DLLFILE%" /tlb:"%windir%\system32\%TLBFILE%" /unregister |
|
75 |
echo. |
|
76 |
echo Unregistering .net 2.0 version if registered |
|
77 |
echo. |
|
78 |
IF EXIST "%windir%\Microsoft.NET\Framework64\v2.0.50727\regasm.exe" "%windir%\Microsoft.NET\Framework64\v2.0.50727\regasm.exe" "%windir%\system32\%DLLFILE%" /tlb:"%windir%\system32\%TLBFILE%" /unregister |
|
79 |
|
|
80 |
echo. |
|
81 |
echo Delete sysnative\%DLLFILE% |
|
82 |
echo. |
|
83 |
DEL "%windir%\sysnative\%DLLFILE%" |
|
84 |
echo. |
|
85 |
echo Delete sysnative\%DLLFILE2% |
|
86 |
echo. |
|
87 |
DEL "%windir%\sysnative\%DLLFILE2%" |
|
88 |
echo. |
|
89 |
echo Delete sysnative\%TLBFILE% |
|
90 |
echo. |
|
91 |
DEL "%windir%\sysnative\%TLBFILE%" |
|
92 |
|
|
93 |
) ELSE ( |
|
94 |
|
|
95 |
ECHO. |
|
96 |
ECHO x64 native mode: sysnative\%DLLFILE% not found so nothing to deinstall |
|
97 |
ECHO. |
|
98 |
) |
|
99 |
|
|
100 |
REM case #2 (this batch runs from x64 console) |
|
101 |
IF EXIST "%windir%\system32\%DLLFILE%" ( |
|
102 |
|
|
103 |
echo. |
|
104 |
echo Unregistering .NET 4.0 version if registered |
|
105 |
echo. |
|
106 |
IF EXIST "%windir%\Microsoft.NET\Framework64\v4.0.30319\regasm.exe" "%windir%\Microsoft.NET\Framework64\v4.0.30319\regasm.exe" "%windir%\system32\%DLLFILE%" /tlb:"%windir%\system32\%TLBFILE%" /unregister |
|
107 |
echo. |
|
108 |
echo Unregistering .NET 2.0 version if registered |
|
109 |
echo. |
|
110 |
IF EXIST "%windir%\Microsoft.NET\Framework64\v2.0.50727\regasm.exe" "%windir%\Microsoft.NET\Framework64\v2.0.50727\regasm.exe" "%windir%\system32\%DLLFILE%" /tlb:"%windir%\system32\%TLBFILE%" /unregister |
|
111 |
|
|
112 |
echo Delete system32\%DLLFILE% |
|
113 |
DEL "%windir%\system32\%DLLFILE%" |
|
114 |
echo Delete system32\%DLLFILE2% |
|
115 |
DEL "%windir%\system32\%DLLFILE2%" |
|
116 |
echo Delete system32\%TLBFILE% |
|
117 |
DEL "%windir%\system32\%TLBFILE%" |
|
118 |
|
|
119 |
) ELSE ( |
|
120 |
|
|
121 |
ECHO. |
|
122 |
ECHO x64 native mode: system32\%DLLFILE% not found so nothing to deinstall |
|
123 |
ECHO. |
|
124 |
) |
|
125 |
|
|
126 |
) ELSE ( |
|
127 |
|
|
128 |
ECHO. |
|
129 |
ECHO x64 native mode: %DLLFILE% not found so nothing to deinstall |
|
130 |
ECHO. |
|
131 |
) |
|
132 |
|
|
133 |
) |
packages/PDFExtractorSDK/FULL/net2.00/Bytescout.PDFExtractor.XML | ||
---|---|---|
1 |
<?xml version="1.0"?> |
|
2 |
<doc> |
|
3 |
<assembly> |
|
4 |
<name>Bytescout.PDFExtractor</name> |
|
5 |
</assembly> |
|
6 |
<members> |
|
7 |
<member name="T:Bytescout.PDFExtractor.AttachmentInfo"> |
|
8 |
<summary> |
|
9 |
Defines various attachment information. |
|
10 |
</summary> |
|
11 |
</member> |
|
12 |
<member name="P:Bytescout.PDFExtractor.AttachmentInfo.Name"> |
|
13 |
<summary> |
|
14 |
Name of the attachment. |
|
15 |
</summary> |
|
16 |
</member> |
|
17 |
<member name="P:Bytescout.PDFExtractor.AttachmentInfo.FileName"> |
|
18 |
<summary> |
|
19 |
Filename for the attachment. |
|
20 |
</summary> |
|
21 |
</member> |
|
22 |
<member name="P:Bytescout.PDFExtractor.AttachmentInfo.FileNameUnicode"> |
|
23 |
<summary> |
|
24 |
Unicode Filename for the attachment (optional). |
|
25 |
</summary> |
|
26 |
</member> |
|
27 |
<member name="P:Bytescout.PDFExtractor.AttachmentInfo.Date"> |
|
28 |
<summary> |
|
29 |
Date of the attachment (optional). |
|
30 |
Default DateTime.MinValue means undefined. |
|
31 |
</summary> |
|
32 |
</member> |
|
33 |
<member name="P:Bytescout.PDFExtractor.AttachmentInfo.DateModified"> |
|
34 |
<summary> |
|
35 |
Date modified (optional). |
|
36 |
Default DateTime.MinValue means undefined. |
|
37 |
</summary> |
|
38 |
</member> |
|
39 |
<member name="P:Bytescout.PDFExtractor.AttachmentInfo.DateCreated"> |
|
40 |
<summary> |
|
41 |
Date created (optional). |
|
42 |
Default DateTime.MinValue means undefined. |
|
43 |
</summary> |
|
44 |
</member> |
|
45 |
<member name="P:Bytescout.PDFExtractor.AttachmentInfo.FolderLocation"> |
|
46 |
<summary> |
|
47 |
Folder location (optional). |
|
48 |
</summary> |
|
49 |
</member> |
|
50 |
<member name="P:Bytescout.PDFExtractor.AttachmentInfo.To"> |
|
51 |
<summary> |
|
52 |
To field (optional). |
|
53 |
</summary> |
|
54 |
</member> |
|
55 |
<member name="P:Bytescout.PDFExtractor.AttachmentInfo.CC"> |
|
56 |
<summary> |
|
57 |
CC field (optional). |
|
58 |
</summary> |
|
59 |
</member> |
|
60 |
<member name="P:Bytescout.PDFExtractor.AttachmentInfo.From"> |
|
61 |
<summary> |
|
62 |
From field (optional). |
|
63 |
</summary> |
|
64 |
</member> |
|
65 |
<member name="P:Bytescout.PDFExtractor.AttachmentInfo.SubjectPrefix"> |
|
66 |
<summary> |
|
67 |
Subject prefix, e.g. "RE: " (optional). |
|
68 |
</summary> |
|
69 |
</member> |
|
70 |
<member name="P:Bytescout.PDFExtractor.AttachmentInfo.Subject"> |
|
71 |
<summary> |
|
72 |
Subject (optional). |
|
73 |
</summary> |
|
74 |
</member> |
|
75 |
<member name="P:Bytescout.PDFExtractor.AttachmentInfo.GUID"> |
|
76 |
<summary> |
|
77 |
GUID (unique id) (optional). |
|
78 |
</summary> |
|
79 |
</member> |
|
80 |
<member name="P:Bytescout.PDFExtractor.AttachmentInfo.Importance"> |
|
81 |
<summary> |
|
82 |
Importance, e.g. "High" (optional). |
|
83 |
</summary> |
|
84 |
</member> |
|
85 |
<member name="P:Bytescout.PDFExtractor.AttachmentInfo.Order"> |
|
86 |
<summary> |
|
87 |
Order (optional). |
|
88 |
</summary> |
|
89 |
</member> |
|
90 |
<member name="P:Bytescout.PDFExtractor.AttachmentInfo.Subtype"> |
|
91 |
<summary> |
|
92 |
Subtype based on MIME types, e.g. "application/pdf" (optional). |
|
93 |
</summary> |
|
94 |
</member> |
|
95 |
<member name="P:Bytescout.PDFExtractor.AttachmentInfo.Description"> |
|
96 |
<summary> |
|
97 |
Description (optional). |
|
98 |
</summary> |
|
99 |
</member> |
|
100 |
<member name="P:Bytescout.PDFExtractor.AttachmentInfo.DisplayName"> |
|
101 |
<summary> |
|
102 |
Display name (optional). |
|
103 |
</summary> |
|
104 |
</member> |
|
105 |
<member name="P:Bytescout.PDFExtractor.AttachmentInfo.Summary"> |
|
106 |
<summary> |
|
107 |
Summary (optional). |
|
108 |
</summary> |
|
109 |
</member> |
|
110 |
<member name="P:Bytescout.PDFExtractor.AttachmentInfo.FileSize"> |
|
111 |
<summary> |
|
112 |
File size (optional). |
|
113 |
</summary> |
|
114 |
</member> |
|
115 |
<member name="P:Bytescout.PDFExtractor.AttachmentInfo.Thumbnail"> |
|
116 |
<summary> |
|
117 |
Thumbnail (preview of the attachment) (optional). |
|
118 |
</summary> |
|
119 |
</member> |
|
120 |
<member name="T:Bytescout.PDFExtractor.AttachmentExtractor"> |
|
121 |
<summary> |
|
122 |
Extracts attachments from PDF file. |
|
123 |
</summary> |
|
124 |
</member> |
|
125 |
<member name="M:Bytescout.PDFExtractor.AttachmentExtractor.#ctor"> |
|
126 |
<summary> |
|
127 |
Initializes a new instance of the <see cref="T:Bytescout.PDFExtractor.AttachmentExtractor" /> class. |
|
128 |
</summary> |
|
129 |
</member> |
|
130 |
<member name="M:Bytescout.PDFExtractor.AttachmentExtractor.#ctor(System.String,System.String)"> |
|
131 |
<summary> |
|
132 |
Initializes a new instance of the <see cref="T:Bytescout.PDFExtractor.AttachmentExtractor" /> class. |
|
133 |
</summary> |
|
134 |
<param name="registrationName">Registration name.</param> |
|
135 |
<param name="registrationKey">Registration key.</param> |
|
136 |
</member> |
|
137 |
<member name="M:Bytescout.PDFExtractor.AttachmentExtractor.LoadDocumentFromStream(System.IO.Stream)"> |
|
138 |
<summary> |
|
139 |
Loads PDF document from provided stream. |
|
140 |
</summary> |
|
141 |
<param name="stream">Input stream.</param> |
|
142 |
</member> |
|
143 |
<member name="P:Bytescout.PDFExtractor.AttachmentExtractor.Count"> |
|
144 |
<summary> |
|
145 |
Returns attachment count. |
|
146 |
</summary> |
|
147 |
</member> |
|
148 |
<member name="M:Bytescout.PDFExtractor.AttachmentExtractor.GetFileName(System.Int32)"> |
|
149 |
<summary> |
|
150 |
Gets the attachment filename. |
|
151 |
</summary> |
|
152 |
<returns>Attachment filename.</returns> |
|
153 |
<param name="index">Attachment index.</param> |
|
154 |
<exception cref="T:Bytescout.PDFExtractor.PDFExtractorException"></exception> |
|
155 |
</member> |
|
156 |
<member name="M:Bytescout.PDFExtractor.AttachmentExtractor.GetSize(System.Int32)"> |
|
157 |
<summary> |
|
158 |
Gets the attachment size (in bytes). |
|
159 |
</summary> |
|
160 |
<returns>Attachment size in bytes.</returns> |
|
161 |
<param name="index">Attachment index.</param> |
|
162 |
<exception cref="T:Bytescout.PDFExtractor.PDFExtractorException"></exception> |
|
163 |
</member> |
|
164 |
<member name="M:Bytescout.PDFExtractor.AttachmentExtractor.GetAttachmentInfo(System.Int32)"> |
|
165 |
<summary> |
|
166 |
Gets the detailed attachment information. |
|
167 |
</summary> |
|
168 |
<param name="index">Attachment index.</param> |
|
169 |
<returns>Attachment information.</returns> |
|
170 |
</member> |
|
171 |
<member name="M:Bytescout.PDFExtractor.AttachmentExtractor.Save(System.Int32,System.String)"> |
|
172 |
<summary> |
|
173 |
Saves the attachment to specified file. |
|
174 |
</summary> |
|
175 |
<returns>True if successful.</returns> |
|
176 |
<param name="index">Attachment index.</param> |
|
177 |
<param name="filename">Output file name.</param> |
|
178 |
<exception cref="T:Bytescout.PDFExtractor.PDFExtractorException"></exception> |
|
179 |
</member> |
|
180 |
<member name="M:Bytescout.PDFExtractor.AttachmentExtractor.SaveToFile(System.Int32,System.String)"> |
|
181 |
<summary> |
|
182 |
Saves the attachment to specified file. |
|
183 |
</summary> |
|
184 |
<returns>True if successful.</returns> |
|
185 |
<param name="index">Attachment index.</param> |
|
186 |
<param name="filename">Output file name.</param> |
|
187 |
<exception cref="T:Bytescout.PDFExtractor.PDFExtractorException"></exception> |
|
188 |
</member> |
|
189 |
<member name="M:Bytescout.PDFExtractor.AttachmentExtractor.Save(System.Int32,System.IO.Stream)"> |
|
190 |
<summary> |
|
191 |
Saves the attachment to stream. |
|
192 |
</summary> |
|
193 |
<param name="index">Attachment index.</param> |
|
194 |
<param name="outputStream">Output stream.</param> |
|
195 |
<returns>True if successful.</returns> |
|
196 |
<exception cref="T:Bytescout.PDFExtractor.PDFExtractorException"></exception> |
|
197 |
</member> |
|
198 |
<member name="M:Bytescout.PDFExtractor.AttachmentExtractor.SaveToStream(System.Int32,System.IO.Stream)"> |
|
199 |
<summary> |
|
200 |
Saves the attachment to stream. |
|
201 |
</summary> |
|
202 |
<param name="index">Attachment index.</param> |
|
203 |
<param name="outputStream">Output stream.</param> |
|
204 |
<returns>True if successful.</returns> |
|
205 |
<exception cref="T:Bytescout.PDFExtractor.PDFExtractorException"></exception> |
|
206 |
</member> |
|
207 |
<member name="T:Bytescout.PDFExtractor.PDFContentType"> |
|
208 |
<summary> |
|
209 |
Defines PDF content types. |
|
210 |
</summary> |
|
211 |
</member> |
|
212 |
<member name="F:Bytescout.PDFExtractor.PDFContentType.Document"> |
|
213 |
<summary> |
|
214 |
(0) Normal document. |
|
215 |
</summary> |
|
216 |
</member> |
|
217 |
<member name="F:Bytescout.PDFExtractor.PDFContentType.Portfolio"> |
|
218 |
<summary> |
|
219 |
(1) Portfolio. |
|
220 |
</summary> |
|
221 |
</member> |
|
222 |
<member name="F:Bytescout.PDFExtractor.PDFContentType.XFAForm"> |
|
223 |
<summary> |
|
224 |
(2) XFA Form. |
|
225 |
</summary> |
|
226 |
</member> |
|
227 |
<member name="T:Bytescout.PDFExtractor.ExtractionAreaUsageMode"> |
|
228 |
<summary> |
|
229 |
Defines how extraction area (if any) is treated when doing text extraction or text search. |
|
230 |
</summary> |
|
231 |
</member> |
|
232 |
<member name="F:Bytescout.PDFExtractor.ExtractionAreaUsageMode.UseAllIntersectingObjects"> |
|
233 |
<summary> |
|
234 |
(0) Extract or search within any text object intersecting with extraction area (if defined). Default mode. |
|
235 |
</summary> |
|
236 |
</member> |
|
237 |
<member name="F:Bytescout.PDFExtractor.ExtractionAreaUsageMode.UseObjectsCompetelyInsideAreaOnly"> |
|
238 |
<summary> |
|
239 |
(1) Extracts or search within text objects which are completely inside extraction area. |
|
240 |
</summary> |
|
241 |
</member> |
|
242 |
<member name="T:Bytescout.PDFExtractor.PageDataCaching"> |
|
243 |
<summary> |
|
244 |
Page data caching behaviour. |
|
245 |
</summary> |
|
246 |
</member> |
|
247 |
<member name="F:Bytescout.PDFExtractor.PageDataCaching.None"> |
|
248 |
<summary> |
|
249 |
Previously accessed page data is not cached and disposed immediately after any other page accessed. Reduces memory usage. |
|
250 |
</summary> |
|
251 |
</member> |
|
252 |
<member name="F:Bytescout.PDFExtractor.PageDataCaching.KeepAllPages"> |
|
253 |
<summary> |
|
254 |
Caches all parsed pages. You can manually dispose cached pages using <see cref="M:Bytescout.PDFExtractor.BaseTextExtractor.DisposePage(System.Int32)" /> method. |
|
255 |
</summary> |
|
256 |
</member> |
|
257 |
<member name="T:Bytescout.PDFExtractor.OngoingOperation"> |
|
258 |
<summary> |
|
259 |
The ongoing operation for <see cref="E:Bytescout.PDFExtractor.BaseExtractor.ProgressChanged" /> event. |
|
260 |
</summary> |
|
261 |
</member> |
|
262 |
<member name="F:Bytescout.PDFExtractor.OngoingOperation.DocumentLoading"> |
|
263 |
<summary> |
|
264 |
Document is being loaded. |
|
265 |
</summary> |
|
266 |
</member> |
|
267 |
<member name="F:Bytescout.PDFExtractor.OngoingOperation.DocumentProcessing"> |
|
268 |
<summary> |
|
269 |
Document is being processed. |
|
270 |
</summary> |
|
271 |
</member> |
|
272 |
<member name="T:Bytescout.PDFExtractor.BaseExtractor"> |
|
273 |
<summary> |
|
274 |
Defines a base class for PDF extractors. |
|
275 |
</summary> |
|
276 |
</member> |
|
277 |
<member name="T:Bytescout.PDFExtractor.BaseExtractor.ProgressEventHandler"> |
|
278 |
<summary> |
|
279 |
Defines Progress event parameters. |
|
280 |
</summary> |
|
281 |
<param name="sender">Event sender.</param> |
|
282 |
<param name="ongoingOperation">Ongoing operaration the progress reported from.</param> |
|
283 |
<param name="progress">Progress value from 0 to 100.</param> |
|
284 |
<param name="cancel">Interruption flag. Set it <c>true</c> to interrupt the processing.</param> |
|
285 |
</member> |
|
286 |
<member name="E:Bytescout.PDFExtractor.BaseExtractor.ProgressChanged"> |
|
287 |
<summary> |
|
288 |
Raised for each reported progress value. Allows to cancel the processing. |
|
289 |
</summary> |
|
290 |
</member> |
|
291 |
<member name="T:Bytescout.PDFExtractor.BaseExtractor.ParsingErrorEventHandler"> |
|
292 |
<summary> |
|
293 |
Defines ParsingError event parameters. |
|
294 |
</summary> |
|
295 |
<param name="sender">Event sender.</param> |
|
296 |
<param name="exceptionInfo">Internal information about the parsing error.</param> |
|
297 |
<param name="abort">Interruption flag. If <c>true</c> the extractor will throw an exception that interrupts the processing.</param> |
|
298 |
</member> |
|
299 |
<member name="E:Bytescout.PDFExtractor.BaseExtractor.ParsingError"> |
|
300 |
<summary> |
|
301 |
Raised on PDF document parsing errors. This usually indicates a damaged document. |
|
302 |
</summary> |
|
303 |
<remarks> |
|
304 |
If this event is handled, and the <c>abort</c> in the event args was set to <c>false</c>, |
|
305 |
the extractor will skip the error and try to process the document further. |
|
306 |
Otherwise the extractor will throw an exception interrupting the processing. |
|
307 |
</remarks> |
|
308 |
</member> |
|
309 |
<member name="E:Bytescout.PDFExtractor.BaseExtractor.PasswordRequired"> |
|
310 |
<summary> |
|
311 |
Occurs when the password required to decrypt the document. |
|
312 |
</summary> |
|
313 |
</member> |
|
314 |
<member name="P:Bytescout.PDFExtractor.BaseExtractor.RegistrationName"> |
|
315 |
<summary> |
|
316 |
Registration name. |
|
317 |
</summary> |
|
318 |
</member> |
|
319 |
<member name="P:Bytescout.PDFExtractor.BaseExtractor.RegistrationKey"> |
|
320 |
<summary> |
|
321 |
Registration key. |
|
322 |
</summary> |
|
323 |
</member> |
|
324 |
<member name="P:Bytescout.PDFExtractor.BaseExtractor.Password"> |
|
325 |
<summary> |
|
326 |
PDF document owner password. |
|
327 |
</summary> |
|
328 |
</member> |
|
329 |
<member name="P:Bytescout.PDFExtractor.BaseExtractor.Version"> |
|
330 |
<summary> |
|
331 |
Gets the component version number. |
|
332 |
</summary> |
|
333 |
</member> |
|
334 |
<member name="P:Bytescout.PDFExtractor.BaseExtractor.Encrypted"> |
|
335 |
<summary> |
|
336 |
Document encryption. |
|
337 |
</summary> |
|
338 |
</member> |
|
339 |
<member name="P:Bytescout.PDFExtractor.BaseExtractor.PageDataCaching"> |
|
340 |
<summary> |
|
341 |
Controls page data caching behavior. |
|
342 |
</summary> |
|
343 |
</member> |
|
344 |
<member name="P:Bytescout.PDFExtractor.BaseExtractor.Profiles"> |
|
345 |
<summary> |
|
346 |
Profiles, applied to object. |
|
347 |
</summary> |
|
348 |
</member> |
|
349 |
<member name="P:Bytescout.PDFExtractor.BaseExtractor.IsDocumentLoaded"> |
|
350 |
<summary> |
|
351 |
Get the document loaded state. |
|
352 |
</summary> |
|
353 |
</member> |
|
354 |
<member name="M:Bytescout.PDFExtractor.BaseExtractor.#ctor"> |
|
355 |
<summary> |
|
356 |
Default constructor. |
|
357 |
</summary> |
|
358 |
</member> |
|
359 |
<member name="M:Bytescout.PDFExtractor.BaseExtractor.#ctor(System.String,System.String)"> |
|
360 |
<summary> |
|
361 |
Initializes a new instance of the extractor class. |
|
362 |
</summary> |
|
363 |
<param name="registrationName">Registration name.</param> |
|
364 |
<param name="registrationKey">Registration key.</param> |
|
365 |
</member> |
|
366 |
<member name="M:Bytescout.PDFExtractor.BaseExtractor.Dispose"> |
|
367 |
<summary> |
|
368 |
Releases the unmanaged resources used by the instance and optionally releases the managed resources. |
|
369 |
</summary> |
|
370 |
</member> |
|
371 |
<member name="M:Bytescout.PDFExtractor.BaseExtractor.Reset"> |
|
372 |
<summary> |
|
373 |
Resets the instance, disposes internal resources and releases the file. |
|
374 |
Use this method before loading another PDF file. |
|
375 |
</summary> |
|
376 |
</member> |
|
377 |
<member name="M:Bytescout.PDFExtractor.BaseExtractor.LoadDocumentFromFile(System.String)"> |
|
378 |
<summary> |
|
379 |
Loads PDF document from specified file. |
|
380 |
Call .Reset() method before loading another file into the same instance so it will release the lock for the file. |
|
381 |
</summary> |
|
382 |
<param name="fileName">File name.</param> |
|
383 |
</member> |
|
384 |
<member name="M:Bytescout.PDFExtractor.BaseExtractor.LoadDocumentFromStream(System.IO.Stream)"> |
|
385 |
<summary> |
|
386 |
Loads PDF document from provided stream. |
|
387 |
</summary> |
|
388 |
<param name="stream">Input stream.</param> |
|
389 |
</member> |
|
390 |
<member name="M:Bytescout.PDFExtractor.BaseExtractor.GetPageCount"> |
|
391 |
<summary> |
|
392 |
Returns document page count. |
|
393 |
</summary> |
|
394 |
<returns>Page count.</returns> |
|
395 |
<exception cref="T:Bytescout.PDFExtractor.PDFExtractorException"></exception> |
|
396 |
</member> |
|
397 |
<member name="M:Bytescout.PDFExtractor.BaseExtractor.GetPageRotationAngle(System.Int32)"> |
|
398 |
<summary> |
|
399 |
Returns the rotation angle of specified page. |
|
400 |
</summary> |
|
401 |
<param name="pageIndex">Index of the page.</param> |
|
402 |
<returns>Rotation angle in degrees.</returns> |
|
403 |
</member> |
|
404 |
<member name="M:Bytescout.PDFExtractor.BaseExtractor.GetPageRectangle(System.Int32)"> |
|
405 |
<summary> |
|
406 |
Gets the page rectangle. |
|
407 |
</summary> |
|
408 |
<param name="pageIndex">Index of the page.</param> |
|
409 |
</member> |
|
410 |
<member name="M:Bytescout.PDFExtractor.BaseExtractor.GetPageRect_Left(System.Int32)"> |
|
411 |
<summary> |
|
412 |
Gets the specified page left coordinate. |
|
413 |
</summary> |
|
414 |
<param name="pageIndex">Index of the page.</param> |
|
415 |
<returns>Left coordinate in points.</returns> |
|
416 |
</member> |
|
417 |
<member name="M:Bytescout.PDFExtractor.BaseExtractor.GetPageRect_Top(System.Int32)"> |
|
418 |
<summary> |
|
419 |
Gets the specified page top coordinate. |
|
420 |
</summary> |
|
421 |
<param name="pageIndex">Index of the page.</param> |
|
422 |
<returns>Top coordinate in points.</returns> |
|
423 |
</member> |
|
424 |
<member name="M:Bytescout.PDFExtractor.BaseExtractor.GetPageRect_Width(System.Int32)"> |
|
425 |
<summary> |
|
426 |
Gets the specified page width. |
|
427 |
</summary> |
|
428 |
<param name="pageIndex">Index of the page.</param> |
|
429 |
<returns>Page width in points.</returns> |
|
430 |
</member> |
|
431 |
<member name="M:Bytescout.PDFExtractor.BaseExtractor.GetPageRect_Height(System.Int32)"> |
|
432 |
<summary> |
|
433 |
Gets the specified page height. |
|
434 |
</summary> |
|
435 |
<param name="pageIndex">Index of the page.</param> |
|
436 |
<returns>Page height in points.</returns> |
|
437 |
</member> |
|
438 |
<member name="P:Bytescout.PDFExtractor.BaseExtractor.ContentType"> |
|
439 |
<summary> |
|
440 |
Returns content type of PDF document: normal document, portfolio or XFA form. |
|
441 |
To extract files from PDF portfolio please use AttachmentExtractor class. |
|
442 |
To extract XFA form content XFAFormExtractor class. |
|
443 |
</summary> |
|
444 |
</member> |
|
445 |
<member name="P:Bytescout.PDFExtractor.BaseExtractor.EmbeddedFileCount"> |
|
446 |
<summary> |
|
447 |
Property is disabled to speed up the document loading. Please use <see cref="T:Bytescout.PDFExtractor.AttachmentExtractor" /> to work with attachments. |
|
448 |
</summary> |
|
449 |
</member> |
|
450 |
<member name="M:Bytescout.PDFExtractor.BaseExtractor.IsEncrypted"> |
|
451 |
<summary> |
|
452 |
Gets the document encrypted state. |
|
453 |
</summary> |
|
454 |
<returns>Encryption state.</returns> |
|
455 |
<exception cref="T:Bytescout.PDFExtractor.PDFExtractorException"></exception> |
|
456 |
</member> |
|
457 |
<member name="P:Bytescout.PDFExtractor.BaseExtractor.CheckPermissions"> |
|
458 |
<summary> |
|
459 |
This option defines if the SDK should check permissions in the PDF document |
|
460 |
and generate PDFExtractorPermissionsException when permissions is not set for the desired action. |
|
461 |
Set to True by default. You should not change it to another value. |
|
462 |
IMPORTANT: THIS OPTION HAVE TO BE ENABLED AND SET TO "TRUE" TO RESPECT OWNERS OF PDF DOCUMENTS. |
|
463 |
IF YOU SET IT TO FALSE TO IGNORE PERMISSIONS WHICH ARE SET IN PDF DOCUMENT THEN |
|
464 |
YOU ARE SOLELY LIABLE FOR THIS ACTION AND FOR ANY COPYRIGHT OR OTHER |
|
465 |
VIOLATIONS AT YOUR OWN RISK. BYTESCOUT IS NOT LIABLE FOR ANY DAMAGES, LOSSES, COPYRIGHT INFRINGEMENTS OR ANY |
|
466 |
OTHER CONSEQUENCES CAUSED BY IGNORING PERMISSIONS OF PDF DOCUMENT. |
|
467 |
BY CHANGING THIS OPTION YOU ARE CONFIRMING YOU ARE UNDERSTANDING ALL WRITTEN ABOVE AND DOING IT AT YOUR OWN RISK. |
|
468 |
</summary> |
|
469 |
</member> |
|
470 |
<member name="P:Bytescout.PDFExtractor.BaseExtractor.ExtractionAreaUsageMode"> |
|
471 |
<summary> |
|
472 |
Controls how an extraction area (if any defined) |
|
473 |
is used when doing a text search to control if we are searching |
|
474 |
within any objects intersecting with an area or only within objects completely inside an area |
|
475 |
</summary> |
|
476 |
</member> |
|
477 |
<member name="M:Bytescout.PDFExtractor.BaseExtractor.SetExtractionArea(System.Drawing.RectangleF)"> |
|
478 |
<summary> |
|
479 |
Sets the extraction area by rectangle. |
|
480 |
</summary> |
|
481 |
<param name="rectangle"></param> |
|
482 |
<remarks> |
|
483 |
Note: the extraction is reset on document loading so set it after the loading. |
|
484 |
</remarks> |
|
485 |
</member> |
|
486 |
<member name="M:Bytescout.PDFExtractor.BaseExtractor.SetExtractionArea(System.Single,System.Single,System.Single,System.Single)"> |
|
487 |
<summary> |
|
488 |
Sets the extraction area by coordinates and dimensions. |
|
489 |
</summary> |
|
490 |
<remarks> |
|
491 |
Note: the extraction is reset on document loading so set it after the loading. |
|
492 |
</remarks> |
|
493 |
</member> |
|
494 |
<member name="M:Bytescout.PDFExtractor.BaseExtractor.ResetExtractionArea"> |
|
495 |
<summary> |
|
496 |
Resets the extraction area to full page. |
|
497 |
</summary> |
|
498 |
</member> |
|
499 |
<member name="M:Bytescout.PDFExtractor.BaseExtractor.LoadProfiles(System.String)"> |
|
500 |
<summary> |
|
501 |
Loads profiles from file. |
|
502 |
</summary> |
|
503 |
<param name="fileName">JSON file containing profiles.</param> |
|
504 |
</member> |
|
505 |
<member name="M:Bytescout.PDFExtractor.BaseExtractor.LoadProfilesFromString(System.String)"> |
|
506 |
<summary> |
|
507 |
Loads profiles from JSON string. |
|
508 |
</summary> |
|
509 |
<param name="jsonString">JSON string containing profiles.</param> |
|
510 |
</member> |
|
511 |
<member name="M:Bytescout.PDFExtractor.BaseExtractor.LoadAndApplyProfiles(System.String)"> |
|
512 |
<summary> |
|
513 |
Loads profiles from JSON string and automatically applies them. |
|
514 |
</summary> |
|
515 |
<remarks>Note, all existing profiles are discarded before loading profiles from the provided string.</remarks> |
|
516 |
<param name="jsonString">JSON string containing profiles.</param> |
|
517 |
</member> |
|
518 |
<member name="T:Bytescout.PDFExtractor.OCRMode"> |
|
519 |
<summary> |
|
520 |
OCR (Optical Character Recognition) usage mode. |
|
521 |
</summary> |
|
522 |
</member> |
|
523 |
<member name="F:Bytescout.PDFExtractor.OCRMode.Off"> |
|
524 |
<summary> |
|
525 |
Off. No OCR is used. |
|
526 |
</summary> |
|
527 |
</member> |
|
528 |
<member name="F:Bytescout.PDFExtractor.OCRMode.Auto"> |
|
529 |
<summary> |
|
530 |
Similar to TextFromImagesAndVectorsAndFonts but checks if the page contains raster images and vector drawings only to decide if should use OCR functionality. |
|
531 |
Runs OCR if page contains almost no text and have 1 or more images / vector drawings so tries to extract text from images and drawings |
|
532 |
The result contains text objects produced from images and vector drawings using OCR functionality if any. |
|
533 |
</summary> |
|
534 |
</member> |
|
535 |
<member name="F:Bytescout.PDFExtractor.OCRMode.TextFromImagesAndVectorsAndFonts"> |
|
536 |
<summary> |
|
537 |
Always runs OCR to extract text from images and vector drawings (if any). |
|
538 |
See also .TextFromImagesAndFonts mode to read from objects except vector drawings. |
|
539 |
The result contains text objects from PDF and text objects produced from images and vector drawings using OCR functionality if any. |
|
540 |
</summary> |
|
541 |
</member> |
|
542 |
<member name="F:Bytescout.PDFExtractor.OCRMode.TextFromImagesAndVectorsAndRepairedFonts"> |
|
543 |
<summary> |
|
544 |
Special mode: extracts text from images and vector drawings and repairs text from fonts fixing the incorrect encoding. |
|
545 |
Some PDF files contain visible text which is damaged when copied (appears as ? or other incorrect symbols when extracted or copied). |
|
546 |
This mode repairs damaged text like that using the OCR functionality. |
|
547 |
The result contains text objects from PDF and text objects produced from images and vector drawings using OCR functionality if any. |
|
548 |
</summary> |
|
549 |
</member> |
|
550 |
<member name="F:Bytescout.PDFExtractor.OCRMode.TextFromRepairedFontsOnly"> |
|
551 |
<summary> |
|
552 |
Special mode: repairs text objects with incorrect encoding using OCR functionality. Images and vectors are not processed in this mode. |
|
553 |
Some PDF files contains visible text which is damaged when copied (appears as ? or other incorrect symbols when extracted or copied). |
|
554 |
This mode repairs damaged text like this using OCR function. |
|
555 |
This mode returns repaired text objects only (no images or vector drawings are processed). |
|
556 |
</summary> |
|
557 |
</member> |
|
558 |
<member name="F:Bytescout.PDFExtractor.OCRMode.TextFromImagesAndRepairedFonts"> |
|
559 |
<summary> |
|
560 |
Special mode: extracts text from raster images (but skips vector drawings) and repairs text objects with incorrect encoding |
|
561 |
Some PDF files contains visible text which is damaged when copied (appears as ? or other incorrect symbols when extracted or copied). |
|
562 |
This mode repairs damaged text like this using the OCR functionality. |
|
563 |
This mode returns repaired text objects and text objects produced from raster images (no vector drawings are processed). |
|
564 |
</summary> |
|
565 |
</member> |
|
566 |
<member name="F:Bytescout.PDFExtractor.OCRMode.TextFromImagesAndFonts"> |
|
567 |
<summary> |
|
568 |
Runs OCR to extract text from images (but skips vector drawings) plus the text objects. |
|
569 |
The result contains text objects from PDF and text objects produced from images (but no vector drawings are processed) using OCR functionality. |
|
570 |
</summary> |
|
571 |
</member> |
|
572 |
<member name="F:Bytescout.PDFExtractor.OCRMode.TextFromImagesOnly"> |
|
573 |
<summary> |
|
574 |
Runs OCR to extract text from images (but skips vector drawings) plus the text objects. |
|
575 |
The result contains text extracted from images only. |
|
576 |
</summary> |
|
577 |
</member> |
|
578 |
<member name="F:Bytescout.PDFExtractor.OCRMode.TextFromVectorsOnly"> |
|
579 |
<summary> |
|
580 |
Runs OCR to extract text from vector drawings only. |
|
581 |
The result contains text objects from vector drawings only. |
|
582 |
</summary> |
|
583 |
</member> |
|
584 |
<member name="F:Bytescout.PDFExtractor.OCRMode.TextFromImagesAndVectorsOnly"> |
|
585 |
<summary> |
|
586 |
Runs OCR to extract text from images and vector drawings only. no text from pdf objects is included. |
|
587 |
The result contains text objects from vector drawings only. |
|
588 |
</summary> |
|
589 |
</member> |
|
590 |
<member name="T:Bytescout.PDFExtractor.OCRCacheMode"> |
|
591 |
<summary> |
|
592 |
OCR results caching behavior. |
|
593 |
Turned off by default (no cache is used). |
|
594 |
In "WholePage" caching mode you may save processing time as the SDK will check if need to re-run OCR on the page |
|
595 |
or can just pull results from previously cached OCR results. |
|
596 |
</summary> |
|
597 |
</member> |
|
598 |
<member name="F:Bytescout.PDFExtractor.OCRCacheMode.Off"> |
|
599 |
<summary> |
|
600 |
no caching enabled |
|
601 |
</summary> |
|
602 |
</member> |
|
603 |
<member name="F:Bytescout.PDFExtractor.OCRCacheMode.WholePage"> |
|
604 |
<summary> |
|
605 |
Whole page is cached. To use the cache extract with OCR from the whole page. |
|
606 |
And then read text data from regions inside page. Text will be taken from the cache for all regions inside the previous page wide region. |
|
607 |
</summary> |
|
608 |
</member> |
|
609 |
<member name="T:Bytescout.PDFExtractor.LineGroupingMode"> |
|
610 |
<summary> |
|
611 |
Sets if lines are not checked to be merged, can be merged by rows, or inside columns |
|
612 |
</summary> |
|
613 |
</member> |
|
614 |
<member name="F:Bytescout.PDFExtractor.LineGroupingMode.None"> |
|
615 |
<summary> |
|
616 |
No lines grouping. Each line is processed as a single row. |
|
617 |
</summary> |
|
618 |
</member> |
|
619 |
<member name="F:Bytescout.PDFExtractor.LineGroupingMode.GroupByRows"> |
|
620 |
<summary> |
|
621 |
Each row is checked against next row to see if these rows can be grouped. |
|
622 |
Rows will be grouped only if all cells in the current row are allowed to be grouped with all cells in next row. |
|
623 |
</summary> |
|
624 |
</member> |
|
625 |
<member name="F:Bytescout.PDFExtractor.LineGroupingMode.GroupByColumns"> |
|
626 |
<summary> |
|
627 |
Each cell is checked against cell below in next row to see if the can be grouped. |
|
628 |
Cells will be grouped inside the same column even if cells in another columns can't be grouped. |
|
629 |
</summary> |
|
630 |
</member> |
|
631 |
<member name="F:Bytescout.PDFExtractor.LineGroupingMode.JoinOrphanedRows"> |
|
632 |
<summary> |
|
633 |
Join row with a single cell up to previous row if there is no separator between them. |
|
634 |
</summary> |
|
635 |
</member> |
|
636 |
<member name="T:Bytescout.PDFExtractor.ColumnDetectionMode"> |
|
637 |
<summary> |
|
638 |
Defines how columns are detected in the text. |
|
639 |
</summary> |
|
640 |
</member> |
|
641 |
<member name="F:Bytescout.PDFExtractor.ColumnDetectionMode.ContentGroupsAndBorders"> |
|
642 |
<summary> |
|
643 |
(0) Based on content groups and borders (vertical lines). |
|
644 |
</summary> |
|
645 |
</member> |
|
646 |
<member name="F:Bytescout.PDFExtractor.ColumnDetectionMode.ContentGroups"> |
|
647 |
<summary> |
|
648 |
(1) Based on content groups only. |
|
649 |
</summary> |
|
650 |
</member> |
|
651 |
<member name="F:Bytescout.PDFExtractor.ColumnDetectionMode.Borders"> |
|
652 |
<summary> |
|
653 |
(2) Based on borders (vertical lines) only. |
|
654 |
</summary> |
|
655 |
</member> |
|
656 |
<member name="F:Bytescout.PDFExtractor.ColumnDetectionMode.BorderedTables"> |
|
657 |
<summary> |
|
658 |
(3) Detects columns inside bordered tables only. Uses optical recognition so may work slower than other modes. |
|
659 |
</summary> |
|
660 |
</member> |
|
661 |
<member name="T:Bytescout.PDFExtractor.BaseTextExtractor"> |
|
662 |
<summary> |
|
663 |
Defines a base class for text-related PDF extractors. |
|
664 |
</summary> |
|
665 |
</member> |
|
666 |
<member name="P:Bytescout.PDFExtractor.BaseTextExtractor.XCoordinateToleranceFactor"> |
|
667 |
<summary> |
|
668 |
X coordinate tolerance factor. |
|
669 |
</summary> |
|
670 |
</member> |
|
671 |
<member name="P:Bytescout.PDFExtractor.BaseTextExtractor.YCoordinateToleranceFactor"> |
|
672 |
<summary> |
|
673 |
Y coordinate tolerance factor. |
|
674 |
</summary> |
|
675 |
</member> |
|
676 |
<member name="P:Bytescout.PDFExtractor.BaseTextExtractor.TableXMinIntersectionRequiredInPercents"> |
|
677 |
<summary> |
|
678 |
Structured extraction (CSV, XML, XLS, StructuredExtractor, TextExtractor with PreserveFormatting = true) |
|
679 |
This option controls how much % of the cell's rectangle should intersect (by X coordinate axis) with previous cell to treat both cells belonging to the same column. |
|
680 |
</summary> |
|
681 |
</member> |
|
682 |
<member name="P:Bytescout.PDFExtractor.BaseTextExtractor.TableYMinIntersectionRequiredInPercents"> |
|
683 |
<summary> |
|
684 |
Y coordinate tolerance factor when working with stuctured (table) data. |
|
685 |
This option controls how much % of the cell rectangle (by Y coordinate) should intersect with row to belong to it. |
|
686 |
</summary> |
|
687 |
</member> |
|
688 |
<member name="P:Bytescout.PDFExtractor.BaseTextExtractor.RTLTextAutoDetectionEnabled"> |
|
689 |
<summary> |
|
690 |
Enables RTL (Right-To-Left) text auto detection. |
|
691 |
</summary> |
|
692 |
</member> |
|
693 |
<member name="P:Bytescout.PDFExtractor.BaseTextExtractor.ExtractInvisibleText"> |
|
694 |
<summary> |
|
695 |
Gets or sets a value indicating whether to extract invisible text from PDF document. |
|
696 |
</summary> |
|
697 |
<value> |
|
698 |
<c>true</c> if extract invisible text; otherwise, <c>false</c>. |
|
699 |
</value> |
|
700 |
</member> |
|
701 |
<member name="P:Bytescout.PDFExtractor.BaseTextExtractor.ExtractShadowLikeText"> |
|
702 |
<summary> |
|
703 |
Gets or sets a value indicating whether to include characters used to create "shadow" effect (when the same character appears with some offset) from PDF document. |
|
704 |
True by default (includes all encoded characters disregarding their real appearance). |
|
705 |
</summary> |
|
706 |
<value> |
|
707 |
<c>true</c> if extract shadow like characters in text; otherwise, <c>false</c>. |
|
708 |
</value> |
|
709 |
</member> |
|
710 |
<member name="P:Bytescout.PDFExtractor.BaseTextExtractor.ExtractAnnotations"> |
|
711 |
<summary> |
|
712 |
Gets or sets a value indicating whether to extract text from annotation objects. Default is <c>true</c>. |
|
713 |
</summary> |
|
714 |
<value> |
|
715 |
<c>true</c> if extract annotations; otherwise, <c>false</c>. |
|
716 |
</value> |
|
717 |
</member> |
|
718 |
<member name="P:Bytescout.PDFExtractor.BaseTextExtractor.Unwrap"> |
|
719 |
<summary> |
|
720 |
Gets or sets a value indicating whether to unwrap lines into single lines or not (especially could be useful in the column layout mode - see ExtractColumnByColumn property). Default is False. |
|
721 |
</summary> |
|
722 |
<remarks>Unwrapping works only when the formatting keeping is disabled (PreserveFormattingOnTextExtraction property is set to False).</remarks> |
내보내기 Unified diff