Some notes on the preparation of a F2-style output text and associated transcriber's notes.
" >> projectID${projectid}/index.html echo "Use UNIX line endings, convert to utf-8 handling simple transliterations (eg., --). Results: text and good word list.
" >> projectID${projectid}/index.html unzip -o projectID${projectid}_F1_saved.zip sh import.sh projectID${projectid}_F1_saved.txt \ projectID${projectid}/input-utf8.txt sh import.sh good_words.txt projectID${projectid}/good_words.utf8 echo Correcting rounds... echo "Fix any mistakes missed by P3/F2. Results: text, or as a diff.
" >> projectID${projectid}/index.html cp fixup.patch projectID${projectid} sh fixup.sh projectID${projectid}/input-utf8.txt \ projectID${projectid}/fixup-utf8.txt echo Correct printer\'s errors... echo "Fix printer's errors as noted by proofreaders. Notes detailing fixed errors are transformed to <corr> form; notes detailing unfixed errors are left untransformed. Results: text.
" >> projectID${projectid}/index.html sh errors.sh projectID${projectid}/fixup-utf8.txt \ projectID${projectid}/errors-utf8.txt echo Validating... echo "Validate the resulting text. Result: log.
" >> projectID${projectid}/index.html sh validate.sh projectID${projectid}/errors-utf8.txt \ > projectID${projectid}/validate-utf8.log echo Fancy quotes... echo "Identify quotation marks and replace them with their curly forms. Apostrophes are left unchanged. Inputs: PG #10688, PG #36485, PG #36833, good words, bad words. Result: text, word analysis log.
" >> projectID${projectid}/index.html sh quotes.sh projectID${projectid}/errors-utf8.txt \ projectID${projectid}/quotes-utf8.txt cp quotes.log projectID${projectid}/quotes-utf8.log cp quotes.good_words quotes.bad_words projectID${projectid} echo Handling hyphens... echo "Rejoin words split across pages. Identify -*ed words and resolve them. Inputs: good words, Result: text, resolution log.
" >> projectID${projectid}/index.html sh hyphen.sh projectID${projectid}/quotes-utf8.txt \ projectID${projectid}/hyphen-utf8.txt cp hyphen.log projectID${projectid}/hyphen-utf8.log cp hyphen.good_words projectID${projectid} echo Handling notes... echo "Remove notes that we've handled. Inputs: handled notes, Result: text.
" >> projectID${projectid}/index.html sh denote.sh projectID${projectid}/hyphen-utf8.txt projectID${projectid}/denote-utf8.txt cp denote.handled projectID${projectid} echo "Word frequency analysis..." echo "Generate a word list, and a matching base word by eliding diacritical marks and hyphens. Replace words identified as bad. Inputs: bad words, Result: text, log.
" >> projectID${projectid}/index.html sh wordfreq.sh projectID${projectid}/denote-utf8.txt \ projectID${projectid}/wordfreq-utf8.txt cp wordfreq.log projectID${projectid}/wordfreq-utf8.log cp wordfreq.bad_words projectID${projectid} echo "Write transcriber's notes..." echo "Use the <corr> markers to generate a list of changes made to the original text and remove the markers from the main text. Result: notes, text.
" >> projectID${projectid}/index.html sh tnotes.sh projectID${projectid}/wordfreq-utf8.txt \ projectID${projectid}/tnotes-utf8.txt projectID${projectid}/tnotes-utf8.notes echo Export... echo "Use DOS line endings. Final result: notes and text.
" >> projectID${projectid}/index.html sh export.sh projectID${projectid}/tnotes-utf8.notes \ projectID${projectid}/output-utf8.notes sh export.sh projectID${projectid}/tnotes-utf8.txt \ projectID${projectid}/output-utf8.txt echo Generating ASCII text output for gutcheck... echo "Strip page markers & blank pages, and join blocks that cross pages. Result: text.
" >> projectID${projectid}/index.html sh rejoin.sh projectID${projectid}/tnotes-utf8.txt \ projectID${projectid}/rejoin-utf8.txt echo "Convert to ASCII by transliterating unicode. Result: text.
" >> projectID${projectid}/index.html sh ascii.sh projectID${projectid}/rejoin-utf8.txt \ projectID${projectid}/ascii-ascii.txt echo "Convert to plain text by indenting /# and /p blocks, and handling <tb>, <sc>, <i>, & <b> (<f> and <g> are discarded). Result: text.
" >> projectID${projectid}/index.html sh text.sh projectID${projectid}/ascii-ascii.txt \ projectID${projectid}/text-ascii.txt echo "Re-wrap text to 72 coloumns honouring /*, /$ and /p no-wrap blocks. Result: text.
" >> projectID${projectid}/index.html sh rewrap.sh projectID${projectid}/text-ascii.txt \ projectID${projectid}/rewrap-ascii.txt echo "Discard /*, /$, /p, and /# block markers. Result: text.
" >> projectID${projectid}/index.html sh undiv.sh projectID${projectid}/rewrap-ascii.txt \ projectID${projectid}/undiv-ascii.txt echo "Use DOS line endings. Result: text.
" >> projectID${projectid}/index.html sh export.sh projectID${projectid}/undiv-ascii.txt \ projectID${projectid}/ascii.txt echo "Run gutcheck. Result: log.
" >> projectID${projectid}/index.html ./tools/gutcheck/gutcheck projectID${projectid}/ascii.txt \ > projectID${projectid}/gutcheck.log echo Running jeebies echo "Run jeebies. Result: log.
" >> projectID${projectid}/index.html ./tools/jeebies/jeebies projectID${projectid}/ascii.txt \ > projectID${projectid}/jeebies.log echo "Strip page markers & blank pages, and join blocks that cross pages. Result: text.
" >> projectID${projectid}/index.html # Note: we don't actually do this step (done in ASCII version above) #sh rejoin.sh projectID${projectid}/tnotes-utf8.txt \ # projectID${projectid}/rejoin-utf8.txt echo "Convert to plain text by indenting /# and /p blocks, and handling <tb>, <sc>, <i>, & <b> (<f> and <g> are discarded). Result: text.
" >> projectID${projectid}/index.html sh text.sh projectID${projectid}/rejoin-utf8.txt \ projectID${projectid}/text-utf8.txt echo "Re-wrap text to 72 coloumns honouring /*, /$ and /p no-wrap blocks. Result: text.
" >> projectID${projectid}/index.html sh rewrap.sh projectID${projectid}/text-utf8.txt \ projectID${projectid}/rewrap-utf8.txt echo "Discard /*, /$, /p, and /# block markers. Result: text.
" >> projectID${projectid}/index.html sh undiv.sh projectID${projectid}/rewrap-utf8.txt \ projectID${projectid}/undiv-utf8.txt echo Spell check... echo "Run a spell check honouring the project's good words list. Result: list of possible misspellings.
" >> projectID${projectid}/index.html sh spell.sh projectID${projectid}/undiv-utf8.txt cp misspellings.utf8 projectID${projectid} echo "" >> projectID${projectid}/index.html echo "" >> projectID${projectid}/index.html (cd projectID${projectid}; lftp -f ../publish.lftp)