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