tesseract-ocr: new package

Signed-off-by: Gilles Talis <gilles.talis@gmail.com>
[Thomas:
 - remove jpeg, tiff and libpng dependencies, they do not seem to be
   used
 - add host-pkgconf as a dependency, since the configure script uses
   PKG_CHECK_MODULES()
 - pass --disable-opencl to explicitly disable OpenCL support
 - add comment to explain why we don't add support for cairo, pango and
   icu as optional dependencies.]
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>

diff --git a/DEVELOPERS b/DEVELOPERS
index 8802fc70c2b4c78cbff7d091b02a103d53611e7f..bdc93d9aad6293cc58697d291e9f3c3117771482 100644 (file)
--- a/DEVELOPERS
+++ b/DEVELOPERS
@@ -589,6 +589,7 @@ F:  package/httping/
 F:     package/iozone/
 F:     package/leptonica/
 F:     package/ocrad/
+F:     package/tesseract-ocr/
 F:     package/webp/
 
 N:     Gregory Dymarek <gregd72002@gmail.com>

diff --git a/package/Config.in b/package/Config.in
index ed480588f6bd9a19ff0ea01a463509f0a7784cba..66c87d558676694fbce17cfc8e8d9e0acbb42786 100644 (file)
--- a/package/Config.in
+++ b/package/Config.in
@@ -244,6 +244,7 @@ comment "Graphic applications"
        source "package/mesa3d-demos/Config.in"
        source "package/qt5cinex/Config.in"
        source "package/rrdtool/Config.in"
+       source "package/tesseract-ocr/Config.in"
 
 comment "Graphic libraries"
        source "package/cegui06/Config.in"

diff --git a/package/tesseract-ocr/Config.in b/package/tesseract-ocr/Config.in
new file mode 100644 (file)
index 0000000..d4c23fb
--- /dev/null
+++ b/package/tesseract-ocr/Config.in
@@ -0,0 +1,43 @@
+comment "tesseract-ocr needs a toolchain w/ threads, C++, gcc >= 4.8, dynamic library"
+       depends on BR2_USE_MMU
+       depends on !BR2_INSTALL_LIBSTDCPP || !BR2_TOOLCHAIN_HAS_THREADS || \
+               !BR2_TOOLCHAIN_GCC_AT_LEAST_4_8 || BR2_STATIC_LIBS
+
+menuconfig BR2_PACKAGE_TESSERACT_OCR
+       bool "tesseract-ocr"
+       depends on BR2_INSTALL_LIBSTDCPP
+       depends on BR2_TOOLCHAIN_HAS_THREADS
+       depends on BR2_TOOLCHAIN_GCC_AT_LEAST_4_8 # C++11
+       depends on BR2_USE_MMU # fork()
+       depends on !BR2_STATIC_LIBS
+       select BR2_PACKAGE_LEPTONICA
+       help
+         Tesseract is an OCR (Optical Character Recognition) engine,
+         It can be used directly, or (for programmers) using an API.
+         It supports a wide variety of languages.
+
+         https://github.com/tesseract-ocr/tesseract
+
+if BR2_PACKAGE_TESSERACT_OCR
+
+comment "tesseract-ocr languages support"
+
+config BR2_PACKAGE_TESSERACT_OCR_LANG_ENG
+       bool "English"
+
+config BR2_PACKAGE_TESSERACT_OCR_LANG_FRA
+       bool "French"
+
+config BR2_PACKAGE_TESSERACT_OCR_LANG_GER
+       bool "German"
+
+config BR2_PACKAGE_TESSERACT_OCR_LANG_SPA
+       bool "Spanish"
+
+config BR2_PACKAGE_TESSERACT_OCR_LANG_CHI_SIM
+       bool "Simplified Chinese"
+
+config BR2_PACKAGE_TESSERACT_OCR_LANG_CHI_TRA
+       bool "Traditional Chinese"
+
+endif

diff --git a/package/tesseract-ocr/tesseract-ocr.hash b/package/tesseract-ocr/tesseract-ocr.hash
new file mode 100644 (file)
index 0000000..9bb5b52
--- /dev/null
+++ b/package/tesseract-ocr/tesseract-ocr.hash
@@ -0,0 +1,8 @@
+# locally computed
+sha256  3fe83e06d0f73b39f6e92ed9fc7ccba3ef734877b76aa5ddaaa778fac095d996  tesseract-ocr-3.05.00.tar.gz
+sha256  c0515c9f1e0c79e1069fcc05c2b2f6a6841fb5e1082d695db160333c1154f06d  eng.traineddata
+sha256  86afb23ad146467f263e8ade56fd3951b1cc28f8c4eebc34f993d3c02d88a7ab  fra.traineddata
+sha256  cb7eb42a7e972cec7ef904fe81825d7b547c46df684c814fdb11a930b13bca3a  deu.traineddata
+sha256  f23985996bbcfe2b57864ccb082783c1c74c87429f04411a04a6ba4d3da2efda  spa.traineddata
+sha256  323ae74d4a2ff49e932dbb4d6282fe0e67ddfafda075ec85803ecd077207454c  chi_sim.traineddata
+sha256  774d566bd0b36e4b6c07415dfa5b6b57feb2575b1f5f231d7fe01a52dac5dd0e  chi_tra.traineddata

diff --git a/package/tesseract-ocr/tesseract-ocr.mk b/package/tesseract-ocr/tesseract-ocr.mk
new file mode 100644 (file)
index 0000000..76ca930
--- /dev/null
+++ b/package/tesseract-ocr/tesseract-ocr.mk
@@ -0,0 +1,72 @@
+################################################################################
+#
+# tesseract-ocr
+#
+################################################################################
+
+TESSERACT_OCR_VERSION = 3.05.00
+TESSERACT_OCR_DATA_VERSION = 3.04.00
+TESSERACT_OCR_SITE = $(call github,tesseract-ocr,tesseract,$(TESSERACT_OCR_VERSION))
+TESSERACT_OCR_LICENSE = Apache-2.0
+TESSERACT_OCR_LICENSE_FILES = COPYING
+
+# Source from github, no configure script provided
+TESSERACT_OCR_AUTORECONF = YES
+
+# cairo, pango and icu are optional dependencies, but only needed for
+# building training tools, which are only built explicitly with "make
+# training", which is not done by this package.
+TESSERACT_OCR_DEPENDENCIES = leptonica host-pkgconf
+TESSERACT_OCR_INSTALL_STAGING = YES
+TESSERACT_OCR_CONF_ENV = \
+       LIBLEPT_HEADERSDIR=$(STAGING_DIR)/usr/include/leptonica
+TESSERACT_OCF_CONF_OPTS = \
+       --disable-opencl
+
+# Language data files download
+ifeq ($(BR2_PACKAGE_TESSERACT_OCR_LANG_ENG),y)
+TESSERACT_OCR_DATA_FILES += eng.traineddata
+endif
+
+ifeq ($(BR2_PACKAGE_TESSERACT_OCR_LANG_FRA),y)
+TESSERACT_OCR_DATA_FILES += fra.traineddata
+endif
+
+ifeq ($(BR2_PACKAGE_TESSERACT_OCR_LANG_DEU),y)
+TESSERACT_OCR_DATA_FILES += deu.traineddata
+endif
+
+ifeq ($(BR2_PACKAGE_TESSERACT_OCR_LANG_SPA),y)
+TESSERACT_OCR_DATA_FILES += spa.traineddata
+endif
+
+ifeq ($(BR2_PACKAGE_TESSERACT_OCR_LANG_CHI_SIM),y)
+TESSERACT_OCR_DATA_FILES += chi_sim.traineddata
+endif
+
+ifeq ($(BR2_PACKAGE_TESSERACT_OCR_LANG_CHI_TRA),y)
+TESSERACT_OCR_DATA_FILES += chi_tra.traineddata
+endif
+
+TESSERACT_OCR_EXTRA_DOWNLOADS = \
+       $(addprefix https://github.com/tesseract-ocr/tessdata/raw/$(TESSERACT_OCR_DATA_VERSION)/,\
+               $(TESSERACT_OCR_DATA_FILES))
+
+define TESSERACT_OCR_PRECONFIGURE
+       # Autoreconf step fails due to missing m4 directory
+       mkdir -p $(@D)/m4
+endef
+
+TESSERACT_OCR_PRE_CONFIGURE_HOOKS += TESSERACT_OCR_PRECONFIGURE
+
+# Language data files installation
+define TESSERACT_OCR_INSTALL_LANG_DATA
+       $(foreach langfile,$(TESSERACT_OCR_DATA_FILES), \
+               $(INSTALL) -D -m 0644 $(DL_DIR)/$(langfile) \
+                       $(TARGET_DIR)/usr/share/tessdata/$(langfile)
+       )
+endef
+
+TESSERACT_OCR_POST_INSTALL_TARGET_HOOKS += TESSERACT_OCR_INSTALL_LANG_DATA
+
+$(eval $(autotools-package))