diff --git a/CHANGELOG.md b/CHANGELOG.md index b6862adc..95c03fd5 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -2,6 +2,69 @@ ## Unreleased +## [v2021-11-30](https://github.com/OCR-D/ocrd_all/releases/v2021-11-30) + +Changed: + + * Re-enable `TESSDATA_PREFIX`, #261 + +### [core](https://github.com/OCR-D/core) [9069a658](https://github.com/OCR-D/core/commits/9069a658)..[c4ca4fab](https://github.com/OCR-D/core/commits/c4ca4fab) + +> Release: [v2.28.0](https://github.com/OCR-D/core/releases/v2.28.0) + + > * :package: v2.28.0 + > * Merge branch 'pr/748' + > * Merge branch 'pr/739' + > * Merge branch 'pr/743' + > * Merge remote-tracking branch 'bertsky/workspace-download-wait' > * :memo: changelog + > * metsHdr/agent/note: add only necessary namespace + > * run_processor: add mets:notes with in/output fileGrp and params via mets:agent + > * allow adding mets:note to mets:agent + > * Merge pull request #737 from OCR-D/update-readme-docs + > * :package: v2.27.0 + > * Merge remote-tracking branch 'bertsky/workspace-remove-allow-empty-regex' + > * Merge branch 'resmgr-undefined-resdict' + > * Merge branch 'fix-workspace-remove-group-fnfe' + > * Merge branch 'rename-group-id' + > * remove undeclared requirement on six, fix #726 + > * bump spec to 3.14.0 + > * :package: v2.26.1 + > * Fixed tesseract resource URL for resource 'configs' + +### [ocrd_segment](https://github.com/OCR-D/ocrd_segment) [34c72c0](https://github.com/OCR-D/ocrd_segment/commits/34c72c0)..[bdc6771](https://github.com/OCR-D/ocrd_segment/commits/bdc6771) + +> Release: [v0.1.11](https://github.com/OCR-D/ocrd_segment/releases/v0.1.11) + + > * evaluate: basic mAP/AR functionality (based on pycocotools) + +### [tesseract](https://github.com/tesseract-ocr/tesseract) [3313bb79](https://github.com/tesseract-ocr/tesseract/commits/3313bb79)..[924b746e](https://github.com/tesseract-ocr/tesseract/commits/924b746e) + +> Release: [5.0.0](https://github.com/tesseract-ocr/tesseract/releases/5.0.0) + + > * Create new release 5.0.0 + > * Merge pull request #3664 from stweil/classify + > * Merge pull request #3663 from stweil/clang7 + > * autobuild: Fix autogen.sh (reduce build time) + > * Remove unused GenericVector::contains_index, UnicityTable::contains_id + > * Remove member function GenericVector::contains + > * Remove member function UnicityTable::contains + +### [workflow-configuration](https://github.com/bertsky/workflow-configuration) [8d3dc73](https://github.com/bertsky/workflow-configuration/commits/8d3dc73)..[af76e39](https://github.com/bertsky/workflow-configuration/commits/af76e39) + + > * PAGE transformation scripts: improve error handling vs options + > * PAGE transformation scripts: cancel if input is not PAGE + > * add PAGE transformation script for namespace update + > * add PAGE transformation scripts for text projection + > * in multi-input case, allow repeating the same input fileGrps + > * update README + > * ocrd-import: avoid additional . in file IDs/names + > * add PAGE transformation script, add comments + > * remove old repair/view rules + > * add+wrap various PAGE transformation scripts + > * ocrd-import: fix backing out of errors + > * ocrd-import: allow upper case suffixes + + ## [v2021-10-12](https://github.com/OCR-D/ocrd_all/releases/v2021-10-12) ### [cor-asv-ann](https://github.com/ASVLeipzig/cor-asv-ann) [1b8c120](https://github.com/ASVLeipzig/cor-asv-ann/commits/1b8c120)..[55e58f0](https://github.com/ASVLeipzig/cor-asv-ann/commits/55e58f0) @@ -1102,8 +1165,6 @@ Hotfix (v2021-05-20 was an incomplete merge) > * Merge pull request #660 from OCR-D/add-guess-mimetype > * Merge pull request #655 from OCR-D/rename-group -Submodule ocrd_anybaseocr contains untracked content -Submodule ocrd_anybaseocr contains modified content ### [ocrd_anybaseocr](https://github.com/OCR-D/ocrd_anybaseocr) [de27915](https://github.com/OCR-D/ocrd_anybaseocr/commits/de27915)..[e63f555](https://github.com/OCR-D/ocrd_anybaseocr/commits/e63f555) > Release: [v1.3.0](https://github.com/OCR-D/ocrd_anybaseocr/releases/v1.3.0) diff --git a/Makefile b/Makefile index f7f33b55..ce0845e7 100644 --- a/Makefile +++ b/Makefile @@ -672,6 +672,7 @@ TESSDATA ?= $(DEFAULT_RESLOC)/ocrd-tesserocr-recognize TESSDATA_RELEASE = 4.1.0 TESSDATA_URL := https://github.com/tesseract-ocr/tessdata_fast/raw/$(TESSDATA_RELEASE) TESSERACT_TRAINEDDATA = $(ALL_TESSERACT_MODELS:%=$(TESSDATA)/%.traineddata) +TESSERACT_TRAINEDDATA += $(ALL_TESSERACT_MODELS:%=$(VIRTUAL_ENV)/share/tessdata/%.traineddata) stripdir = $(patsubst %/,%,$(dir $(1))) @@ -693,14 +694,14 @@ $(TESSDATA)/%.traineddata: $(call WGET,$@,$(TESSDATA_URL)/$(notdir $(call stripdir,$@))/$(notdir $@)) || \ { $(RM) $@; false; } +$(VIRTUAL_ENV)/share/tessdata/%.traineddata: $(TESSDATA)/%.traineddata + cp $< $@ + tesseract/Makefile.in: tesseract cd tesseract && ./autogen.sh # Build and install Tesseract. -# We do not want to compile-in TESSDATA_PREFIX here, because our preferred TESSDATA path -# would still get incorrectly suffixed by "/tessdata" at runtime. -# Instead, we will rely on TESSDATA_PREFIX=$(TESSDATA) as a shell variable for the standalone CLI. -TESSERACT_CONFIG ?= --disable-tessdata-prefix --disable-openmp --disable-shared CXXFLAGS="-g -O2 -fPIC" +TESSERACT_CONFIG ?= --disable-openmp --disable-shared CXXFLAGS="-g -O2 -fPIC" $(BIN)/tesseract: tesseract/Makefile.in mkdir -p $(VIRTUAL_ENV)/build/tesseract cd $(VIRTUAL_ENV)/build/tesseract && $(CURDIR)/tesseract/configure --prefix="$(VIRTUAL_ENV)" $(TESSERACT_CONFIG) diff --git a/core b/core index 9069a658..c4ca4fab 160000 --- a/core +++ b/core @@ -1 +1 @@ -Subproject commit 9069a6581f37ec1c189e8cfaa62692fb66004964 +Subproject commit c4ca4fabff53e31f3f9d2a070c5936dda566a469 diff --git a/ocrd_segment b/ocrd_segment index 34c72c03..bdc67719 160000 --- a/ocrd_segment +++ b/ocrd_segment @@ -1 +1 @@ -Subproject commit 34c72c038cb2688781ad61bf926fc66842115368 +Subproject commit bdc67719cf4d5e758162ae54c0998f54b9610514 diff --git a/tesseract b/tesseract index c676d5bc..924b746e 160000 --- a/tesseract +++ b/tesseract @@ -1 +1 @@ -Subproject commit c676d5bcffae99f486769e57c5e9dc9e37531d62 +Subproject commit 924b746e6f8e02e634188de1f15c8a95ebe9680b diff --git a/workflow-configuration b/workflow-configuration index 8d3dc730..af76e39a 160000 --- a/workflow-configuration +++ b/workflow-configuration @@ -1 +1 @@ -Subproject commit 8d3dc7303544830c7fe8ab12a72cd6f4f753dc3b +Subproject commit af76e39a2c86d67960afc6a3eaf17fbb09cb3b6b