images=$(sort $(wildcard images/*)) # @andre make wildcard so that it takes any image file but doesn't take the listimg.txt file images-tiff=$(sort $(wildcard images-tiff/*.tiff)) input-hocr=$(sort $(wildcard hocr/*)) output_ocr:=$(dir_ocr)/output.txt tmpfile:= $(shell mktemp) space:= $(empty) $(empty) newline:= '\n' listimgs:= $(subst $(space),$(newline), $(images) ) # list of the images, with one filename on each line $(subst $(delimitator),$(replacement),$(list)) OS:= $(shell uname) # Colors: add color to output ie @echo $(color_r) output text color_w:="\033[0;29m" color_r:="\033[0;31m" color_g:="\033[0;32m" color_b:="\033[0;34m" # HELP / SELF DOCUMENTATION # rules where first line contains comment with 2x# (see example in clean rule) .DEFAULT_GOAL := help # help rule as default when you run: make .PHONY: help help: @grep -E '^[a-zA-Z_-\/]+:.*?## .*$$' $(MAKEFILE_LIST) | sort | awk 'BEGIN {FS = ":.*?## "}; {printf "\033[36m%-30s\033[0m %s\n", $$1, $$2}' # CLEAN clean: ## removes output (target) files rm ocr/output.txt rm $(tmpfile) # ADMINISTRATIVE RECIPES dirs: ## create the dirs in working dir @-mkdir -p images/ @-mkdir -p images-tiff/ @-mkdir -p output/ @-mkdir -p output/erase-replace/ @-mkdir -p ocr/ @-mkdir -p hocr/ @echo $(color_r)'Directories made': ocr/ hocr/ images/ images-tiff/ output/ testif: ifeq ($(OS),Darwin) @echo $(OS) endif # POST-PROCESSING RECIPES ocr/output.txt: ## ocr with tesseract echo $(listimgs) > $(@D)/list.txt @echo $(basename $@ .txt) tesseract $(@D)/list.txt $(basename $@ .txt) python3 src/build_database.py $(@) tiffs: ## convert images/ to images-tiff/ Depends on IM echo $(images) for i in $(images); \ do tiff=`basename $$i .jpg`.tiff; \ convert -density 300 $$i -colorspace RGB -type truecolor -alpha on images-tiff/$$tiff; \ echo $$tiff; \ done; hocrs: ## hocr with tesseract and then change extension to .html for i in images-tiff/*.tiff; \ do echo $$i; hocrfile=`basename $$i .tiff`; \ tesseract $$i hocr/$$hocrfile hocr; \ mv hocr/$$hocrfile.hocr hocr/$$hocrfile.html; \ done; #OUTPUT GENERATION RECIPES reading_structure: ocr/output.txt ## Analyzes OCR'ed text using a Part of Speech (POS) tagger. Outputs a string of tags (e.g. nouns, verbs, adjectives, and adverbs). Dependencies: python3's nltk, jinja2, weasyprint mkdir -p output/reading_structure cp src/reading_structure/jquery.min.js output/reading_structure cp src/reading_structure/script.js output/reading_structure cp src/reading_structure/style.css output/reading_structure cat $< | python3 src/reading_structure/reading_structure.py weasyprint -s src/reading_structure/print-noun.css output/reading_structure/index.html output/reading_structure/poster_noun.pdf weasyprint -s src/reading_structure/print-adv.css output/reading_structure/index.html output/reading_structure/poster_adv.pdf weasyprint -s src/reading_structure/print-dppt.css output/reading_structure/index.html output/reading_structure/poster_dppt.pdf weasyprint -s src/reading_structure/print-stopword.css output/reading_structure/index.html output/reading_structure/poster_stopword.pdf weasyprint -s src/reading_structure/print-neutral.css output/reading_structure/index.html output/reading_structure/poster_neutral.pdf weasyprint -s src/reading_structure/print-entity.css output/reading_structure/index.html output/reading_structure/poster_named_entities.pdf x-www-browser output/reading_structure/index.html output/chatbot.txt: ocr/output.txt ## Comments a text with a simple chatbot. Dependencies: python3's chatterbot cat $< | python3 src/textbotconversation.py $(@) output/n7.txt: ocr/output.txt ## Replaces nouns with the 7th noun that follows. Dependencies: 91k_nouns cat $< | python3 src/n_7.py > $(@) carlandre: ocr/output.txt ## Alice: Creates visual poetry out of a text. Dependencies: pytest @python3 src/carlandre.py .PHONY: carlandre # cat $(@) > /dev/usb/lp0 overunder: ocr/output.txt ## Alice: An interpreted language that translate simple weaving instructions and creates a weaving pattern on text. @python3 src/overunder.py .PHONY: overunder erase: tiffs hocrs ## Natasha: Analyzes pages in order, erases least common words from view. Dependencies: PIL, html5lib, FPDF python3 src/erase_leastcommon.py rm $(input-hocr) rm $(images-tiff) replace:tiffs hocrs ## Natasha: Analyzes pages in order, replace least common words with most common words. Dependencies: PIL, html5lib, FPDF python3 src/replace_leastcommon.py rm $(input-hocr) rm $(images-tiff) visualization: $(images) $(tmpfile) ##Creates data visualization from images/*.jpg. Dependencies: mplayer @echo $(tmpfile) for i in $(images); do \ cat $$i >> $(tmpfile); \ done; ifeq ($(OS),Darwin) cat $(tmpfile) | mplayer -sws 4 -zoom -vf dsize=720:720 -demuxer rawvideo -rawvideo w=56:h=64:i420:fps=25 -; else cat $(tmpfile) | mplayer -vo x11 -sws 4 -zoom -vf dsize=720:720 -demuxer rawvideo -rawvideo w=50:h=50:i420:fps=25 -; endif ttssr-human-only: ocr/output.txt ## Loop: text to speech-speech recognition. Dependencies: espeak, pocketsphinx bash src/ttssr-loop-human-only.sh ocr/output.txt chatbook: ocr/output.txt #chatbot based on the knowledge of the scans Dependencies: nltk_rake, irc, nltk python3 src/chatbook.py