Merge pull request #835 from stweil/3.05

3.05: Backports from master branch

.travis.yml

@@ -2,16 +2,16 @@ language: cpp
 
 notifications:
   email: false
-  
+
 sudo: required
 
 os:
   - linux
-  #- osx
+  - osx
 
-branches:
-  only:
-    - master
+#branches:
+  #only:
+    #- master
 
 addons:
   apt:
@@ -24,17 +24,17 @@ addons:
 before_install:
   - if [[ $TRAVIS_OS_NAME == linux   ]]; then LINUX=true; fi
   - if [[ $TRAVIS_OS_NAME == osx     ]]; then OSX=true; fi
-
-  - if [[ $OSX ]]; then brew update; fi
 
-  - export LEPT_VER=1.73
+  #- if [[ $OSX ]]; then brew update; fi
+
+  - export LEPT_VER=1.74.1
 
 install:
-  - if [[ $OSX ]]; then brew install icu4c pango; brew link --force gettext; fi
-  - if [[ $OSX ]]; then export ICU_ROOT=/usr/local/opt/icu4c ; fi
-  - wget https://www.cmake.org/files/v3.6/cmake-3.6.1-Linux-x86_64.sh
-  - sudo sh cmake-3.6.1-Linux-x86_64.sh --skip-license --prefix=/usr
-  - wget -O leptonica.zip https://github.com/DanBloomberg/leptonica/archive/v$LEPT_VER.zip
+  #- if [[ $OSX ]]; then brew install icu4c pango; brew link --force gettext; fi
+  #- if [[ $OSX ]]; then export ICU_ROOT=/usr/local/opt/icu4c ; fi
+  - if [[ $LINUX ]]; then wget https://www.cmake.org/files/v3.7/cmake-3.7.2-Linux-x86_64.sh; fi
+  - if [[ $LINUX ]]; then sudo sh cmake-3.7.2-Linux-x86_64.sh --skip-license --prefix=/usr; fi
+  - wget -O leptonica.zip https://github.com/DanBloomberg/leptonica/archive/$LEPT_VER.zip
   - unzip leptonica.zip -d .
   - cmake -Hleptonica-$LEPT_VER -Bleptonica-$LEPT_VER/build
   - make -C leptonica-$LEPT_VER/build

CMakeLists.txt

@@ -44,7 +44,7 @@ set(VERSION_MAJOR 3)
 set(VERSION_MINOR 05)
 set(VERSION_PLAIN ${VERSION_MAJOR}.${VERSION_MINOR})
 
-set(MINIMUM_LEPTONICA_VERSION 1.71)
+set(MINIMUM_LEPTONICA_VERSION 1.74)
 
 if(NOT EXISTS ${PROJECT_SOURCE_DIR}/.cppan)
     if (NOT Leptonica_DIR AND NOT MSVC)

COPYING

@@ -17,5 +17,5 @@ in this distribution is now licensed under the Apache License:
 Other Dependencies and Licenses:
 ================================
 
-Tesseract uses Leptonica library (http://leptonica.com/) with a very weakly
-restricted copyright license (http://leptonica.com/about-the-license.html)
+Tesseract uses Leptonica library (http://leptonica.com/) which essentially
+uses a BSD 2-clause license. (http://leptonica.com/about-the-license.html)

ChangeLog

@@ -13,6 +13,7 @@
   * Added new C API for orientation and script detection, removed the old one.
   * Increased minimum autoconf version to 2.59.
   * Removed dead code.
+  * Require Leptonica 1.74 or higher.
   * Fixed many compiler warning.
   * Fixed memory and resource leaks.
   * Fixed some issues with the 'Cube' OCR engine.
@@ -63,7 +64,7 @@
     text and truetype fonts.
   * Added support for PDF output with searchable text.
   * Removed entire IMAGE class and all code in image directory.
-  * Tesseract executable: support for output to stdout; limited support for one 
+  * Tesseract executable: support for output to stdout; limited support for one
     page images from stdin  (especially on Windows)
   * Added Renderer to API to allow document-level processing and output
     of document formats, like hOCR, PDF.
@@ -148,12 +149,12 @@
   * Added TessdataManager to combine data files into a single file.
   * Some dead code deleted.
   * VC++6 no longer supported. It can't cope with the use of templates.
-  * Many more languages added. 
+  * Many more languages added.
   * Doxygenation of most of the function header comments.
   * Added man pages.
   * Added bash completion script (issue 247: thanks to neskiem)
   * Fix integer overview in thresholding (issue 366: thanks to Cyanide.Drake)
-  * Add Danish Fraktur support (issues 300, 360: thanks to 
+  * Add Danish Fraktur support (issues 300, 360: thanks to
     dsl602230@vip.cybercity.dk)
   * Fix file pointer leak (issue 359, thanks to yukihiro.nakadaira)
   * Fix an error using user-words (Issue 345: thanks to max.markin)
@@ -162,7 +163,7 @@
   * Fix an automake error (Issue 318, thanks to ichanjz)
   * Fix a Win32 crash on fileFormatIsTiff() (Issues 304, 316, 317, 330, 347,
     349, 352: thanks to nguyenq87, max.markin, zdenop)
-  * Fixed a number of errors in newer (stricter) versions of VC++ (Issues 
+  * Fixed a number of errors in newer (stricter) versions of VC++ (Issues
     301, among others)
 
 2009-06-30 - V2.04

api/Makefile.am

@@ -45,7 +45,7 @@ endif
 libtesseract_api_la_SOURCES = baseapi.cpp capi.cpp renderer.cpp pdfrenderer.cpp
 
 lib_LTLIBRARIES += libtesseract.la
-libtesseract_la_LDFLAGS = $(OPENCL_LDFLAGS)
+libtesseract_la_LDFLAGS = $(LEPTONICA_LIBS) $(OPENCL_LDFLAGS)
 libtesseract_la_SOURCES =
 # Dummy C++ source to cause C++ linking.
 # see http://www.gnu.org/s/hello/manual/automake/Libtool-Convenience-Libraries.html#Libtool-Convenience-Libraries

api/pdfrenderer.cpp

@@ -703,11 +703,6 @@ bool TessPDFRenderer::imageToPDFObj(Pix *pix,
   L_COMP_DATA *cid = NULL;
   const int kJpegQuality = 85;
 
-  // TODO(jbreiden) Leptonica 1.71 doesn't correctly handle certain
-  // types of PNG files, especially if there are 2 samples per pixel.
-  // We can get rid of this logic after Leptonica 1.72 is released and
-  // has propagated everywhere. Bug discussion as follows.
-  // https://code.google.com/p/tesseract-ocr/issues/detail?id=1300
   int format, sad;
   findFileFormat(filename, &format);
   if (pixGetSpp(pix) == 4 && format == IFF_PNG) {

ccmain/equationdetect.cpp

@@ -625,10 +625,6 @@ void EquationDetect::IdentifySeedParts() {
 }
 
 float EquationDetect::ComputeForegroundDensity(const TBOX& tbox) {
-#if LIBLEPT_MINOR_VERSION < 69 && LIBLEPT_MAJOR_VERSION <= 1
-  // This will disable the detector because no seed will be identified.
-  return 1.0f;
-#else
   Pix *pix_bi = lang_tesseract_->pix_binary();
   int pix_height = pixGetHeight(pix_bi);
   Box* box = boxCreate(tbox.left(), pix_height - tbox.top(),
@@ -640,7 +636,6 @@ float EquationDetect::ComputeForegroundDensity(const TBOX& tbox) {
   boxDestroy(&box);
 
   return fract;
-#endif
 }
 
 bool EquationDetect::CheckSeedFgDensity(const float density_th,

configure.ac

@@ -411,53 +411,27 @@ AC_CHECK_TYPES([mbstate_t],,, [#include "wchar.h"])
 # Test auxiliary packages
 # ----------------------------------------
 
-# Check location of leptonica/liblept headers.
-AC_MSG_CHECKING([for leptonica])
-AC_ARG_VAR([LIBLEPT_HEADERSDIR], [Leptonica headers directory])
-
-have_lept=no
-if test "$LIBLEPT_HEADERSDIR" = "" ; then
-  LIBLEPT_HEADERSDIR="/usr/local/include /usr/include /opt/local/include/leptonica"
-fi
-for incd in $LIBLEPT_HEADERSDIR
-do
-  for lept in . leptonica liblept
-  do
-    if test -r "$incd/$lept/allheaders.h" ; then
-      CPPFLAGS="$CPPFLAGS -I$incd/$lept"
-      have_lept=yes
-    fi
-  done
-done
-
-if test "$have_lept" = yes ; then
-  AC_MSG_RESULT(yes)
-  AC_CHECK_LIB([lept], [l_generateCIDataForPdf], [],
-               [AC_MSG_ERROR([leptonica library with pdf support (>= 1.71) is missing])])
+PKG_CHECK_MODULES([LEPTONICA], [lept >= 1.74], [have_lept=true], [have_lept=false])
+if $have_lept; then
+  CPPFLAGS="$CPPFLAGS $LEPTONICA_CFLAGS"
 else
-  AC_MSG_ERROR([leptonica not found])
+  AC_MSG_ERROR([Leptonica 1.74 or higher is required. Try to install libleptonica-dev package.])
 fi
 
-AC_MSG_CHECKING([leptonica headers version >= 1.74])
-AC_PREPROC_IFELSE(
-    [AC_LANG_PROGRAM([#include "allheaders.h"],
-[#if (LIBLEPT_MAJOR_VERSION >= 1) && (LIBLEPT_MINOR_VERSION >= 74)
-int i = 0;
-#else
-#error You need to upgrade your leptonica library!
-#endif])],
-    [AC_MSG_RESULT(yes)],
-    [AC_MSG_FAILURE([leptonica 1.74 or higher is required])])
-
 AM_CONDITIONAL([ENABLE_TRAINING], true)
 
 # Check location of icu headers
-have_icu=false
-AC_CHECK_HEADERS([unicode/uchar.h], [have_icu=true], [have_icu=false])
-if !($have_icu); then
+PKG_CHECK_MODULES([ICU_UC], [icu-uc], [have_icu_uc=true], [have_icu_uc=false])
+PKG_CHECK_MODULES([ICU_I18N], [icu-i18n], [have_icu_i18n=true], [have_icu_i18n=false])
+if !($have_icu_uc && $have_icu_i18n); then
+  AC_CHECK_HEADERS([unicode/uchar.h], [have_icu=true], [have_icu=false])
+  if !($have_icu); then
         AC_MSG_WARN([Training tools WILL NOT be built because of missing icu library.])
         AC_MSG_WARN([Try to install libicu-devel package.])
         AM_CONDITIONAL([ENABLE_TRAINING], false)
+  else
+    ICU_UC_LIBS="-licui18n -licuuc"
+  fi
 fi
 
 # Check location of pango headers

opencl/oclkernels.h

@@ -7,8 +7,10 @@
 // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 // See the License for the specific language governing permissions and
 // limitations under the License.
-#ifndef _OCL_KERNEL_H_
-#define _OCL_KERNEL_H_
+
+#ifndef TESSERACT_OPENCL_OCLKERNELS_H_
+#define TESSERACT_OPENCL_OCLKERNELS_H_
+
 #ifndef USE_EXTERNAL_KERNEL
 #define KERNEL( ... )# __VA_ARGS__ "\n"
 // Double precision is a default of spreadsheets
@@ -1210,5 +1212,5 @@ KERNEL(
  ; // close char*
 
 #endif  // USE_EXTERNAL_KERNEL
-#endif  //_OCL_KERNEL_H_
+#endif  // TESSERACT_OPENCL_OCLKERNELS_H_
 /* vim:set shiftwidth=4 softtabstop=4 expandtab: */