sm-commit AT lists.ibiblio.org
Subject: Source Mage code commit list
List archive
[SM-Commit] GIT changes to master grimoire by Treeve Jelbert (1e89c66debf87764ab258b4625acda0296ab0607)
- From: Treeve Jelbert <scm AT sourcemage.org>
- To: sm-commit AT lists.ibiblio.org
- Subject: [SM-Commit] GIT changes to master grimoire by Treeve Jelbert (1e89c66debf87764ab258b4625acda0296ab0607)
- Date: Mon, 29 Oct 2018 13:55:46 +0000
GIT changes to master grimoire by Treeve Jelbert <treeve AT sourcemage.org>:
graphics/tesseract/CONFIGURE | 1
graphics/tesseract/DEPENDS | 6 +++-
graphics/tesseract/DETAILS | 56
+++++++++++++++++++++++--------------------
graphics/tesseract/HISTORY | 7 +++++
graphics/tesseract/INSTALL | 4 +--
graphics/tesseract/PRE_BUILD | 21 ++++++++--------
6 files changed, 56 insertions(+), 39 deletions(-)
New commits:
commit 1e89c66debf87764ab258b4625acda0296ab0607
Author: Treeve Jelbert <treeve AT sourcemage.org>
Commit: Treeve Jelbert <treeve AT sourcemage.org>
tesseract: => 4.0.0
diff --git a/graphics/tesseract/CONFIGURE b/graphics/tesseract/CONFIGURE
new file mode 100755
index 0000000..b2f02c3
--- /dev/null
+++ b/graphics/tesseract/CONFIGURE
@@ -0,0 +1 @@
+source $GRIMOIRE/CMAKE_CONFIGURE
diff --git a/graphics/tesseract/DEPENDS b/graphics/tesseract/DEPENDS
index 802b192..2a45f6b 100755
--- a/graphics/tesseract/DEPENDS
+++ b/graphics/tesseract/DEPENDS
@@ -1,6 +1,10 @@
+source $GRIMOIRE/CMAKE_DEPENDS &&
depends -sub CXX gcc &&
depends JPEG &&
depends leptonica &&
depends tiff &&
depends icu &&
-optional_depends pango '' '' 'build training tools, improve OpenType support'
+optional_depends pango \
+ ' -DBUILD_TRAINING_TOOLS=1' \
+ ' -DBUILD_TRAINING_TOOLS=0' \
+ 'build training tools, improve OpenType support'
diff --git a/graphics/tesseract/DETAILS b/graphics/tesseract/DETAILS
index 547e312..f104cf1 100755
--- a/graphics/tesseract/DETAILS
+++ b/graphics/tesseract/DETAILS
@@ -1,42 +1,44 @@
+source $GRIMOIRE/CMAKE_FUNCTIONS
SPELL=tesseract
- VERSION=3.05.02
- LANGVER=3.02
-
SOURCE_HASH=sha512:4cb23a6981dd5ec9eefea7b9674847ae88a411a7308ee6d946a920c76eefcf5fe7a90f6cb3ff00493a0e69b5c327d052fa8514d7f3ed506bccbe4b0163065793
+ VERSION=4.0.0
+ LANGVER=4.00
+
SOURCE_HASH=sha512:69e57d4ba1fc43d212fd0fff69a2b5d48a3b37cfee7054fdc083cbb7e04d92317609a32e457229661d70ce8d9b16c9d25e81bfc3861db660dd2c8f292202d447
URI=https://github.com/tesseract-ocr/tesseract/archive
+DAT=https://github.com/tesseract-ocr/tessdata/raw/$LANGVER
SOURCE=$SPELL-$VERSION.tar.gz
SOURCE_URL[0]=$URI/$VERSION.tar.gz
for LL in $TESS_LANG; do
case $LL in
eng)
- SOURCE2=$SPELL-ocr-$LANGVER.eng.tar.gz
- SOURCE2_URL[0]=$URI/$SOURCE2
-
SOURCE2_HASH=sha512:4db016a3809be03855c41363788907f404e08aa277cf891e86de5f0d7da5f4f9fd76f6e19a2a983a7906a94c8235e66608fefe45e0bdc786e44e613896d1f48c
+ SOURCE2=$LL.traineddata-$LANGVER
+ SOURCE2_URL[0]=$DAT/$LL.traineddata
+
SOURCE2_HASH=sha512:dec017b60c7ee7c8dfe1c4cef562a02c8699c2856d6562641a7077c1a0b5493a26085fa81e7dfff97323054276f24eb51f64833bc2fe7bbe91b1955c6f719618
;;
fra)
- SOURCE3=$SPELL-ocr-$LANGVER.fra.tar.gz
- SOURCE3_URL[0]=$URI/$SOURCE3
-
SOURCE3_HASH=sha512:d10a23acb0dd4128c00a5c3d90ceace55601d2847b60a59d4d268252ac04f5d3917c98fceff02dc7e98fd1ec7233332d56ba53d71da73044f8547e5c19da2209
+ SOURCE3=$LL.traineddata-$LANGVER
+ SOURCE3_URL[0]=$DAT/$LL.traineddata
+
SOURCE3_HASH=sha512:ecf1ded66b3e5c903161377903b5a693ea8221b155ac61fa88b0e2ba1fdb34cce8d8e6d0270a45ed822baa012d7d24ee15c6032a31b62d9b773106e39bd18603
;;
ita)
- SOURCE4=$SPELL-ocr-$LANGVER.ita.tar.gz
- SOURCE4_URL[0]=$URI/$SOURCE4
-
SOURCE4_HASH=sha512:20246685d0d092de96ebddadf2ae981ab9035c0735ae7cfafc6aa943a009516649a32e6db06a61932218b4c6a1e9dc33dad5fd403207fe1982f598d06d7800d3
+ SOURCE4=$LL.traineddata-$LANGVER
+ SOURCE4_URL[0]=$DAT/$LL.traineddata
+
SOURCE4_HASH=sha512:0e32802292edb6bde1300a28af43e720e8cd6ea28e236865b01f8f5ff7b2e04b88d5d1ff2c32bf4fe20691c01aee4e524411c4cabb612e881e7573dc836ed0e6
;;
nld)
- SOURCE5=$SPELL-ocr-$LANGVER.nld.tar.gz
- SOURCE5_URL[0]=$URI/$SOURCE5
-
SOURCE5_HASH=sha512:ee00ddb20a8ecb18ff6dbe5211bccb7bd7cf7342df8b7da29f3bde3677c8a2a24cbd99400f25224e2a2432955c11026277af8f98852016c95d349259eb746f1c
+ SOURCE5=$LL.traineddata-$LANGVER
+ SOURCE5_URL[0]=$DAT/$LL.traineddata
+
SOURCE5_HASH=sha512:248ac4048b8909e325bd3ca4edbe48f9853eb8fdd8ad9d1950a557706fe45832ada8dac9dbbf033d33fe676101fa81f96de1c691465b77ad84e29f1307eb2846
;;
spa)
- SOURCE6=$SPELL-ocr-$LANGVER.spa.tar.gz
- SOURCE6_URL[0]=$URI/$SOURCE6
-
SOURCE6_HASH=sha512:cd7d9cc6e83d13fed9ee7921a8f22ff8c52be043802abdd545d6b9b17f5fb8d10bd55b26131c790ceb9a09359c73af9e850ac927f7be687690c29b5e638c8d32
+ SOURCE6=$LL.traineddata-$LANGVER
+ SOURCE6_URL[0]=$DAT/$LL.traineddata
+
SOURCE6_HASH=sha512:5d009401faa71d3a8e9c4ff32dd1efc5e38c02b8c4170653ebb33874e6c489f7556c67ce6ca7cee27500496f657cf4361314563576176ff5e545b8079722bb8f
;;
deu)
- SOURCE7=$SPELL-ocr-$LANGVER.deu.tar.gz
- SOURCE7_URL[0]=$URI/$SOURCE6
-
SOURCE7_HASH=sha512:897b62ca9befa884c1bea640ef1b6be9a9ef975ab68b07e434d61f1cce21419ac303c0110005f30f8cdd47102f6dc9b742effc185b6d4fe62026343e77cce602
+ SOURCE7=$LL.traineddata-$LANGVER
+ SOURCE7_URL[0]=$DAT/$LL.traineddata
+
SOURCE7_HASH=sha512:23326861284f096e40834bac31ef4e9344507b9332c8bbdc10dced0c60743bb2fbeae79d888c80c56e796661a2232998f1f7ba64ff1e0c9bc79ff13bd0a2663c
;;
*)
message language $LL not yet supported
@@ -51,9 +53,11 @@ SOURCE_DIRECTORY=$BUILD_DIRECTORY/$SPELL-$VERSION
KEYWORDS="ocr"
SHORT="ocr engine"
cat << EOF
-A commercial quality OCR engine originally developed at HP between 1985
-and 1995.
-In 1995, this engine was among the top 3 evaluated by UNLV. It was
-open-sourced by
-HP and UNLV in 2005
+This package contains an OCR engine - libtesseract and a command line
+program - tesseract. Tesseract 4 adds a new neural net (LSTM) based OCR
+engine which is focused on line recognition, but also still supports the
+legacy Tesseract OCR engine of Tesseract 3 which works by recognizing
+character patterns. Compatibility with Tesseract 3 is enabled by using the
+Legacy OCR Engine mode (--oem 0). It also needs traineddata files which
+support the legacy engine, for example those from the tessdata repository.
EOF
diff --git a/graphics/tesseract/HISTORY b/graphics/tesseract/HISTORY
index 78556c1..37c1eac 100644
--- a/graphics/tesseract/HISTORY
+++ b/graphics/tesseract/HISTORY
@@ -1,3 +1,10 @@
+2018-10-29 Treeve Jelbert <treeve AT sourcemage.org>
+ * DETAILS: version 4.0.0
+ update description
+ all the training data files have been updated
+ * DEPENDS DETAILS INSTALL PRE_BUILD: adapt to cmake build
+ * PRE_BUILD INSTALL: new trained data files
+
2018-07-18 Florian Franzmann <siflfran AT hawo.stw.uni-erlangen.de>
* DETAILS: version 3.05.02
diff --git a/graphics/tesseract/INSTALL b/graphics/tesseract/INSTALL
index 2694684..d7f1949 100755
--- a/graphics/tesseract/INSTALL
+++ b/graphics/tesseract/INSTALL
@@ -1,3 +1,3 @@
-default_install &&
+cmake_install &&
cd "$SOURCE_DIRECTORY" &&
-mv -v tesseract-ocr/tessdata/* "$INSTALL_ROOT/usr/share/tessdata"
+cp -a tess-trained "$INSTALL_ROOT/usr/share"
diff --git a/graphics/tesseract/PRE_BUILD b/graphics/tesseract/PRE_BUILD
index 6ae045f..2b0e433 100755
--- a/graphics/tesseract/PRE_BUILD
+++ b/graphics/tesseract/PRE_BUILD
@@ -1,14 +1,15 @@
-default_pre_build &&
-cd $SOURCE_DIRECTORY &&
-cd $SOURCE_DIRECTORY &&
- autoreconf -f -i --symlink &&
+default_pre_build &&
+cd $SOURCE_DIRECTORY &&
+mkdir -p tess-trained &&
+cd tess-trained &&
+
for LL in $TESS_LANG; do
case $LL in
- eng) unpack_file 2 ;;
- fra) unpack_file 3 ;;
- ita) unpack_file 4 ;;
- nld) unpack_file 5 ;;
- spa) unpack_file 6 ;;
- deu) unpack_file 7 ;;
+ eng) verify_file 2 && cp $SOURCE_CACHE/$SOURCE2 . ;;
+ fra) verify_file 3 && cp $SOURCE_CACHE/$SOURCE2 . ;;
+ ita) verify_file 4 && cp $SOURCE_CACHE/$SOURCE2 . ;;
+ nld) verify_file 5 && cp $SOURCE_CACHE/$SOURCE2 . ;;
+ spa) verify_file 6 && cp $SOURCE_CACHE/$SOURCE2 . ;;
+ deu) verify_file 7 && cp $SOURCE_CACHE/$SOURCE2 . ;;
esac
done
- [SM-Commit] GIT changes to master grimoire by Treeve Jelbert (1e89c66debf87764ab258b4625acda0296ab0607), Treeve Jelbert, 10/29/2018
Archive powered by MHonArc 2.6.24.