Merge pull request #364 from stweil/build_rules

Remove build rules for Tesseract and Leptonica

.gitignore

@@ -7,8 +7,6 @@ data/unicharset
 dta19-reduced
 dta19-reduced.tar.gz
 *.built
-tesseract-*
-leptonica-*
 *.BAK
 /usr
 data/checkpoints

Makefile

@@ -47,15 +47,6 @@ LAST_CHECKPOINT = $(OUTPUT_DIR)/checkpoints/$(MODEL_NAME)_checkpoint
 # Name of the proto model. Default: '$(PROTO_MODEL)'
 PROTO_MODEL = $(OUTPUT_DIR)/$(MODEL_NAME).traineddata
 
-# No of cores to use for compiling leptonica/tesseract. Default: $(CORES)
-CORES = 4
-
-# Leptonica version. Default: $(LEPTONICA_VERSION)
-LEPTONICA_VERSION := 1.83.0
-
-# Tesseract commit. Default: $(TESSERACT_VERSION)
-TESSERACT_VERSION := 5.3.0
-
 # Tesseract model repo to use. Default: $(TESSDATA_REPO)
 TESSDATA_REPO = _best
 
@@ -131,9 +122,6 @@ help: default
 	@echo "    training         Start training"
 	@echo "    traineddata      Create best and fast .traineddata files from each .checkpoint file"
 	@echo "    proto-model      Build the proto model"
-	@echo "    leptonica        Build leptonica"
-	@echo "    tesseract        Build tesseract"
-	@echo "    tesseract-langs  Download minimal stock models"
 	@echo "    tesseract-langdata  Download stock unicharsets"
 	@echo "    clean-box        Clean generated .box files"
 	@echo "    clean-lstmf      Clean generated .lstmf files"
@@ -154,9 +142,6 @@ help: default
 	@echo "    PUNC_FILE          Optional Punc file for Punctuation dawg. Default: $(PUNC_FILE)"
 	@echo "    START_MODEL        Name of the model to continue from. Default: '$(START_MODEL)'"
 	@echo "    PROTO_MODEL        Name of the proto model. Default: '$(PROTO_MODEL)'"
-	@echo "    CORES              No of cores to use for compiling leptonica/tesseract. Default: $(CORES)"
-	@echo "    LEPTONICA_VERSION  Leptonica version. Default: $(LEPTONICA_VERSION)"
-	@echo "    TESSERACT_VERSION  Tesseract commit. Default: $(TESSERACT_VERSION)"
 	@echo "    TESSDATA_REPO      Tesseract model repo to use (_fast or _best). Default: $(TESSDATA_REPO)"
 	@echo "    MAX_ITERATIONS     Max iterations. Default: $(MAX_ITERATIONS)"
 	@echo "    EPOCHS             Set max iterations based on the number of lines for the training. Default: none"
@@ -181,7 +166,7 @@ endif
 
 .PRECIOUS: $(LAST_CHECKPOINT)
 
-.PHONY: default clean help leptonica lists proto-model tesseract tesseract-langs tesseract-langdata training unicharset charfreq
+.PHONY: default clean help lists proto-model tesseract-langdata training unicharset charfreq
 
 ALL_FILES = $(and $(wildcard $(GROUND_TRUTH_DIR)),$(shell find -L $(GROUND_TRUTH_DIR) -name '*.gt.txt'))
 unexport ALL_FILES # prevent adding this to envp in recipes (which can cause E2BIG if too long; cf. make #44853)
@@ -375,42 +360,6 @@ $(TESSERACT_LANGDATA):
 	@mkdir -p $(@D)
 	wget -O $@ 'https://github.com/tesseract-ocr/langdata_lstm/raw/main/$(@F)'
 
-# Build leptonica
-leptonica: leptonica.built
-
-leptonica.built: leptonica-$(LEPTONICA_VERSION)
-	cd $< ; \
-		./configure --prefix=$(LOCAL) && \
-		make -j$(CORES) install SUBDIRS=src && \
-		date > "$@"
-
-leptonica-$(LEPTONICA_VERSION): leptonica-$(LEPTONICA_VERSION).tar.gz
-	tar xf "$<"
-
-leptonica-$(LEPTONICA_VERSION).tar.gz:
-	wget 'http://www.leptonica.org/source/$@'
-
-# Build tesseract
-tesseract: tesseract.built tesseract-langs
-
-tesseract.built: tesseract-$(TESSERACT_VERSION)
-	cd $< && \
-		sh autogen.sh && \
-		PKG_CONFIG_PATH="$(LOCAL)/lib/pkgconfig" \
-			./configure --prefix=$(LOCAL) && \
-		LDFLAGS="-L$(LOCAL)/lib"\
-			make -j$(CORES) install && \
-		LDFLAGS="-L$(LOCAL)/lib"\
-			make -j$(CORES) training-install && \
-		date > "$@"
-
-tesseract-$(TESSERACT_VERSION):
-	wget https://github.com/tesseract-ocr/tesseract/archive/$(TESSERACT_VERSION).zip
-	unzip $(TESSERACT_VERSION).zip
-
-# Download tesseract-langs
-tesseract-langs: $(TESSDATA)/eng.traineddata
-
 $(TESSDATA)/%.traineddata:
 	wget -O $@ 'https://github.com/tesseract-ocr/tessdata$(TESSDATA_REPO)/raw/main/$(@F)'
 

README.md

@@ -1,6 +1,6 @@
 # tesstrain
 
-> Training workflow for Tesseract 4 as a Makefile for dependency tracking and building the required software from source.
+> Training workflow for Tesseract 5 as a Makefile for dependency tracking.
 
 ## Install
 
@@ -10,27 +10,15 @@ You will need at least GNU `make` (minimal version 4.2), `wget`, `find`, `bash`,
 
 ### Leptonica, Tesseract
 
-You will need a recent version (>= 4.0.0beta1) of tesseract built with the
+You will need a recent version (>= 5.3) of tesseract built with the
 training tools and matching leptonica bindings.
-[Build](https://github.com/tesseract-ocr/tesseract/wiki/Compiling)
-[instructions](https://github.com/tesseract-ocr/tesseract/wiki/Compiling-%E2%80%93-GitInstallation)
-and more can be found in the [Tesseract project
-wiki](https://github.com/tesseract-ocr/tesseract/wiki/).
-
-Alternatively, you can build leptonica and tesseract within this project and install it to a subdirectory `./usr` in the repo:
-
-```sh
-  make leptonica tesseract
-```
-
-Tesseract will be built from the git repository, which requires CMake,
-autotools (including autotools-archive) and some additional libraries for the
-training tools. See the [installation notes in the tesseract
-repository](https://github.com/tesseract-ocr/tesseract/blob/main/INSTALL.GIT.md).
+[Build](https://tesseract-ocr.github.io/tessdoc/Compiling)
+[instructions](https://tesseract-ocr.github.io/tessdoc/Compiling-%E2%80%93-GitInstallation)
+and more can be found in the [Tesseract User Manual](https://tesseract-ocr.github.io/tessdoc/).
 
 #### Windows
 
-  1. Install the latest tesseract (e.g. from https://digi.bib.uni-mannheim.de/tesseract/) make sure that tesseract is add to your PATH.
+  1. Install the latest tesseract (e.g. from https://digi.bib.uni-mannheim.de/tesseract/), make sure that tesseract is added to your PATH.
   2. Install [Python 3](https://www.python.org/downloads/)
   3. Install [Git SCM to Windows](https://gitforwindows.org/) - it provides a lot of linux utilities on Windows (e.g. `find`, `unzip`, `rm`) and put `C:\Program Files\Git\usr\bin` to the begining of your PATH variable (temporarely you can do it in `cmd` with `set PATH=C:\Program Files\Git\usr\bin;%PATH%` - unfornatelly there are several Windows tools with the same name as on linux (`find`, `sort`) with different behaviour/functionality and there is need to avoid them during training.
   4. Install winget/[Windows Package Manager](https://github.com/microsoft/winget-cli/releases/) and then run `winget install GnuWin32.Make` and `winget install wget` to install missing tools.
@@ -110,9 +98,6 @@ Run `make help` to see all the possible targets and variables:
     training         Start training
     traineddata      Create best and fast .traineddata files from each .checkpoint file
     proto-model      Build the proto model
-    leptonica        Build leptonica
-    tesseract        Build tesseract
-    tesseract-langs  Download minimal stock models
     tesseract-langdata  Download stock unicharsets
     clean            Clean all generated files
 
@@ -127,9 +112,6 @@ Run `make help` to see all the possible targets and variables:
     DATA_DIR           Data directory for output files, proto model, start model, etc. Default: data
     OUTPUT_DIR         Output directory for generated files. Default: DATA_DIR/MODEL_NAME
     GROUND_TRUTH_DIR   Ground truth directory. Default: OUTPUT_DIR-ground-truth
-    CORES              No of cores to use for compiling leptonica/tesseract. Default: 4
-    LEPTONICA_VERSION  Leptonica version. Default: 1.78.0
-    TESSERACT_VERSION  Tesseract commit. Default: 4.1.1
     TESSDATA_REPO      Tesseract model repo to use (_fast or _best). Default: _best
     TESSDATA           Path to the .traineddata directory to start finetuning from. Default: ./usr/share/tessdata
     MAX_ITERATIONS     Max iterations. Default: 10000