diff -Nru gimagereader-3.1.91/CMakeLists.txt gimagereader-3.1.99/CMakeLists.txt --- gimagereader-3.1.91/CMakeLists.txt 2016-05-03 14:24:07.000000000 +0000 +++ gimagereader-3.1.99/CMakeLists.txt 2016-10-13 21:45:35.000000000 +0000 @@ -7,7 +7,7 @@ # Project properties PROJECT(gimagereader) SET(PACKAGE_NAME gImageReader) -SET(PACKAGE_VERSION 3.1.91) +SET(PACKAGE_VERSION 3.1.99) SET(PACKAGE_LOCALE_DIR "${CMAKE_INSTALL_PREFIX}/share/locale") @@ -62,18 +62,21 @@ IF(UNIX) PKG_CHECK_MODULES(SANE sane-backends) ENDIF(UNIX) +SET(PODOFO_LDFLAGS -lpodofo) INCLUDE_DIRECTORIES(${CMAKE_BINARY_DIR} ${TESSERACT_INCLUDE_DIRS} ${SANE_INCLUDE_DIRS}) IF("${INTERFACE_TYPE}" STREQUAL "gtk") PKG_CHECK_MODULES(GTKMM REQUIRED gtkmm-3.0) PKG_CHECK_MODULES(GTKSOURCEVIEWMM REQUIRED gtksourceviewmm-3.0) - PKG_CHECK_MODULES(GTKSPELLMM REQUIRED gtkspellmm-3.0>=3.0.4) + PKG_CHECK_MODULES(GTKSPELLMM REQUIRED gtkspellmm-3.0>=3.0.5) PKG_CHECK_MODULES(CAIROMM REQUIRED cairomm-1.0) PKG_CHECK_MODULES(PANGOMM REQUIRED pangomm-1.4) PKG_CHECK_MODULES(POPPLER REQUIRED poppler-glib) PKG_CHECK_MODULES(JSONGLIB REQUIRED json-glib-1.0) PKG_CHECK_MODULES(LIBXMLPP REQUIRED libxml++-2.6) + PKG_CHECK_MODULES(LIBJPEG REQUIRED libjpeg) + PKG_CHECK_MODULES(FONTCONFIG REQUIRED fontconfig) INCLUDE_DIRECTORIES( ${GTKMM_INCLUDE_DIRS} ${GTKSOURCEVIEWMM_INCLUDE_DIRS} @@ -83,6 +86,8 @@ ${POPPLER_INCLUDE_DIRS} ${JSONGLIB_INCLUDE_DIRS} ${LIBXMLPP_INCLUDE_DIRS} + ${LIBJPEG_INCLUDE_DIRS} + ${FONTCONFIG_INCLUDE_DIRS} ) SET(gimagereader_LIBS ${GTKMM_LDFLAGS} @@ -93,6 +98,9 @@ ${POPPLER_LDFLAGS} ${JSONGLIB_LDFLAGS} ${LIBXMLPP_LDFLAGS} + ${LIBJPEG_LDFLAGS} + ${PODOFO_LDFLAGS} + ${FONTCONFIG_LDFLAGS} ) SET(srcdir "gtk") ELSEIF("${INTERFACE_TYPE}" STREQUAL "qt4") @@ -102,7 +110,7 @@ PKG_CHECK_MODULES(POPPLER REQUIRED poppler-qt4) PKG_CHECK_MODULES(QJSON REQUIRED QJson) INCLUDE_DIRECTORIES(${QTSPELL_INCLUDE_DIRS} ${POPPLER_INCLUDE_DIRS} ${QJSON_INCLUDE_DIRS}) - SET(gimagereader_LIBS ${QTSPELL_LDFLAGS} ${POPPLER_LDFLAGS} ${QJSON_LDFLAGS}) + SET(gimagereader_LIBS ${QTSPELL_LDFLAGS} ${POPPLER_LDFLAGS} ${QJSON_LDFLAGS} ${PODOFO_LDFLAGS}) SET(srcdir "qt") ELSEIF("${INTERFACE_TYPE}" STREQUAL "qt5") SET(CMAKE_AUTOMOC ON) @@ -114,7 +122,7 @@ PKG_CHECK_MODULES(QTSPELL REQUIRED QtSpell-qt5>=0.8.0) PKG_CHECK_MODULES(POPPLER REQUIRED poppler-qt5) INCLUDE_DIRECTORIES(${QTSPELL_INCLUDE_DIRS} ${POPPLER_INCLUDE_DIRS}) - SET(gimagereader_LIBS ${QTSPELL_LDFLAGS} ${POPPLER_LDFLAGS}) + SET(gimagereader_LIBS ${QTSPELL_LDFLAGS} ${POPPLER_LDFLAGS} ${PODOFO_LDFLAGS}) SET(srcdir "qt") ELSE() MESSAGE(FATAL_ERROR "Invalid interface type ${INTERFACE_TYPE}") diff -Nru gimagereader-3.1.91/data/gimagereader.appdata.xml.in gimagereader-3.1.99/data/gimagereader.appdata.xml.in --- gimagereader-3.1.91/data/gimagereader.appdata.xml.in 2016-05-03 14:24:07.000000000 +0000 +++ gimagereader-3.1.99/data/gimagereader.appdata.xml.in 2016-10-13 21:45:35.000000000 +0000 @@ -5,18 +5,26 @@ CC0-1.0 GPL-3.0+ gImageReader + gImageReader

A graphical frontend to tesseract-ocr

Grafická nadstavba pro engine tesseract-ocr

+ + ocr + optical + recognition + tesseract + pdf + -

gImageReader is a simple OCR application which acts as a frontend to the tesseract OCR engine. Features include:

gImageReader is a simple optical character recognition (OCR) application which acts as a frontend to the tesseract OCR engine. Features include:

Automatic page layout detection
User can manually define and adjust recognition regions
Import images from disk, scanning devices, clipboard and screenshots
Supports multipage PDF documents
Import PDF documents and images from disk, scanning devices, clipboard and screenshots
Process multiple images and documents in one go
Manual or automatic recognition area definition
Recognize to plain text or to hOCR documents
Recognized text displayed directly next to the image
Basic editing of output text, including search/replace and removing line breaks
Spellchecking for output text (if corresponding dictionary installed)
Post-process the recognized text, including spellchecking
Generate PDF documents from hOCR documents

@@ -38,5 +46,6 @@ https://github.com/manisandro/gImageReader - manisandro@gmail.com - \ No newline at end of file + http://the-web-site-with-translation-instructions/ + manisandro@gmail.com + diff -Nru gimagereader-3.1.91/data/manual.html.in gimagereader-3.1.99/data/manual.html.in --- gimagereader-3.1.91/data/manual.html.in 2016-05-03 14:24:07.000000000 +0000 +++ gimagereader-3.1.99/data/manual.html.in 2016-10-13 21:45:35.000000000 +0000 @@ -46,6 +46,47 @@

News

A detailed list of changes can be found in the commit log: https://github.com/manisandro/gImageReader/commits/master

gImageReader 3.1.99 (Oct 13 2016):

gImageReader 3.2 release candidate
General improvements:

Catch critical tesseract errors which otherwise result in the application crashing
Improve spelling dictionary auto-installation logic
Allow choosing whether to store language files (language definitions, spelling dictionaries) in system-wide or user-local directories

Plain text mode improvements: +
- Allow recognizing user-defined regions on multiple pages
- Also tread \u2014 character as a hyphen
- Make preserve paragraphs option correctly deal with trailing whitespace
+
hOCR editor improvements: +
- Add "Add to dictionary" and "Ignore word" actions to spell-checking menu in hOCR editor
- Exclude non-word characters from spell-checking
- Allow merging adjacent word items
- Allow adjusting bounding boxes of document elements by resizing the selection in the canvas
- Allow removing arbitrary items from the document tree
- Allow defining custom graphic regions from context-menu of the respective page item
+
PDF export improvements: +
- Add previewing capability
- Take into account baseline information to better position the words in the generated PDF
- Add options to choose color format and compression of images written to PDF, allowing to greatly reduce the size of PDF
- Correctly handle paper size and DPI
- Improve logic for uniformizing word and line spacing
- Make sure correct hypen character is used, allowing PDF applications to correctly find hyphenated words
+
New and updated translations
Various bug fixes
Full details in commit log: https://github.com/manisandro/gImageReader/commits/master

gImageReader 3.1.91 (May 03 2016):

gImageReader 3.2 beta 2
To perform OCR on an image, the user needs to specify:
- The input images (e.g. images to recognize),
- The recognition mode (e.g. plain text vs hOCR, PDF,
- The recognition mode (e.g. plain text vs hOCR, PDF)
- The recognition language(s).
Alternatively, the automatic layout detection button, accessible from the main toolbar will attempt to automatically define appropriate recognition areas, as well as adjust the rotation of the image if necessary.
Selections can be deleted and reordered via the context menu which appears when right-clicking on them. It is also possible to resize existing selections by dragging the corners of the selection rectangle.
The selected portions of the image (or the entire image, if no selections are defined) can be recognized by pressing on the recognize button in the main toolbar. Alternatively, individual areas can be recognized by right-clicking a selection. From the selection context menu, it is also possible to redirect the recognized text to the clipboard, instead of the output pane.
If multiple pages are selected for recognition, the program allows the user to choose between either recognizing the full area of each individual page, or performing a page-layout analysis on each page to automatically detect appropriate recognition areas.
If multiple pages are selected for recognition, the program allows the user to choose between either recognizing the full resp. manually selected area for each individual page, or performing a page-layout analysis on each page to automatically detect appropriate recognition areas.
Recognized text will appear in the output pane (unless the text was redirected to the clipboard), which is shown automatically as soon as some text was recognized.
If a spelling dictionary for the recognition language is available, automatic spell-checking will be enabled for the outputted text. The used spelling dictionary can be changed either from the language menu next to the recognize button, or from the menu which appears when right-clicking in the text area.
When additional text is recognized, it will either get appended, inserted at cursor position, or replace the previous content of the text buffer, depending on the mode selected in the append mode menu, which can be found in the output pane toolbar.

Recognizing and post-processing in hOCR, PDF mode

In hOCR mode, the entire page of the selected source(s) is recognized.
In hOCR mode, always the entire page of the selected source(s) is recognized.
The recognition result is presented in the output pane as a tree-structure, divided in pages, paragraphs, textlines, words and graphics.
When an entry in the tree-structure is selected, the corresponding area is highlighted in the image. Additionally, formatting and layout properties of the entry are shown in the Properties tab below the document tree. The raw hOCR source is visible in the Source tab below the document tree.
The word text in the document tree can be edited by double-clicking the respective word entry. If a word is mis-spelled, it will be rendered red. Right-clicking a word in the document tree will show a menu with spelling suggestions.
Properties for a selected entry can be modified by double clicking the desired property value in the Properties tab. Interesting actions for text entries are tweaking the bounding area, changing the language and modifying the font size. The language property also definies the spelling language used to check the respective word.
Properties for a selected entry can be modified by double clicking the desired property value in the Properties tab. Interesting actions for text entries are tweaking the bounding area, changing the language and modifying the font size. The language property also definies the spelling language used to check the respective word. The bounding area can also be edited by resizing the selection rectangle in the canvas.
Adjacent word items can be merged by rightclicking the respective selected items.
Arbitrary items can be removed from the document via right-click on the respective item.
New graphic areas can be defined by selecting the Add graphic region entry of the context menu of the respective page item and drawing a rectangle on the canvas.
The document tree can be saved as a hOCR HTML document via the Save as hOCR text button in the output pane toolbar. Existing documents can be imported via the Open hOCR file button in the output pane toolbar.
PDF files can be generated from the PDF export menu in the output pane toolbar. Two modes are available:
- PDF will generate a reconstructed PDF the same layout and graphics/pictures as the source document. When exporting, the user is prompted for the font family to use, whether to honour the font sizes detected by the OCR engine, and whether to attempt to homogenize the text line spacing.
- PDF will generate a reconstructed PDF the same layout and graphics/pictures as the source document.
- PDF with invisible text overlay will generate a PDF with the unmodified source image as background and invisible (but selectable) text overlayed above the respective source text in the image. This export mode is usefull for generating a document which is visually identical to the input, but with searchable and selectable text.
When exporting to PDF, the user is prompted for the font family to use, whether to honour the font sizes detected by the OCR engine, and whether to attempt to homogenize the text line spacing. Also, the user can select the color format, resolution and compression method to use for images in the PDF document to control the size of the generated output.

News

Recognizing and post-processing in hOCR, PDF mode

Program options

Installation of tesseract language definitions