lhess2021
4 years ago
11 changed files with 0 additions and 24665 deletions
File diff suppressed because it is too large
File diff suppressed because it is too large
File diff suppressed because it is too large
@ -1,114 +0,0 @@ |
|||
import re |
|||
import os |
|||
|
|||
canto_dir = os.path.abspath(os.getcwd()) |
|||
print('\n\n====================' + canto_dir + '====================') |
|||
|
|||
""" |
|||
Define XML file name |
|||
Load txt file |
|||
Iterate through lines in txt file |
|||
Iterate through words in each line |
|||
Iterate through each letter from end to beginning |
|||
catch single chars like `-` |
|||
catch single chars at end of line like `-\n` |
|||
if the char is not `’` or `-` or alphabetical, go to the next letter in word (backwards) |
|||
else separate the ending punct from beginning chars |
|||
Iterate through each letter from beginning to remainder of word |
|||
if no punctuation, then all remainder is middle chars |
|||
catch single chars like `-\n` |
|||
if the char is not `‘` or `’` or `-` or alphabetical, go to the next letter in word (forwards) |
|||
else separate middle chars from beginning punctuation |
|||
Build the tag word from <beginning punct> + <middle chars> + <ending punct> |
|||
Write the tag word to the temp XML file |
|||
Open the temp XML file |
|||
Iterate over lines |
|||
Catch double spaces |
|||
Catch leading spaces |
|||
Add leading tabs and leading line tag |
|||
Add closing line tag |
|||
|
|||
""" |
|||
|
|||
def add_tags(canto_txt_file): |
|||
# only grab 0xx-canticle from `*.txt` file names |
|||
xmlfile = canto_txt_file.split('.')[0] + '.xml' |
|||
tmpxmlfile = '.' + canto_txt_file.split('.')[0] + '.tmp.xml' |
|||
with open(xmlfile,'w') as cxml: |
|||
with open(tmpxmlfile,'w') as cxmltmp: |
|||
with open(canto_txt_file,'r') as ctxt: |
|||
for spaced_line in ctxt: |
|||
# use `~` as a placeholder for spaces later |
|||
line = re.sub(' ','~',spaced_line) |
|||
words = line.split('~') |
|||
for i in range(len(words)): |
|||
word = words[i] |
|||
# Iterate from ending to beginning of word |
|||
L = len(word) - 1 |
|||
# Catch single chars like `-` |
|||
if L == 0: |
|||
before_end_word_chars = word |
|||
ending_punct_chars = '' |
|||
# Catch single chars at end of line |
|||
elif L == 1 and '\n' in word: |
|||
before_end_word_chars = word.rstrip() |
|||
ending_punct_chars = '\n' |
|||
else: |
|||
print('Got to <- with: ' + word + ' and this L: ' + str(L) + ' in ' + canto_txt_file) |
|||
# We need `word[L] != '-'` because there are some words like `-:` |
|||
while word[L] != '’' and word[L] != '-' and not word[L].isalpha(): |
|||
L-=1 |
|||
else: |
|||
ending_punct_begin_index = L + 1 |
|||
ending_punct_chars = word[ending_punct_begin_index:] |
|||
before_end_word_chars = word[:ending_punct_begin_index] |
|||
# Iterate from start to remainder of word |
|||
L = len(word) - 1 |
|||
if L == 0: |
|||
middle_word_chars = word |
|||
starting_punct_chars = '' |
|||
elif L == 1 and '\n' in word: |
|||
middle_word_chars = word.rstrip() |
|||
starting_punct_chars = '' |
|||
else: |
|||
print('Got -> with this word: ' + word + ' and this L: ' + str(L) + ' in ' + canto_txt_file) |
|||
while word[-L - 1] != '‘' and word[-L - 1] != '’' and word[L] != '-' and not word[-L - 1].isalpha(): |
|||
L-=1 |
|||
else: |
|||
starting_punct_end_index = -L - 1 |
|||
starting_punct_chars = word[:starting_punct_end_index] |
|||
middle_word_chars = before_end_word_chars[-L-1:] |
|||
# Pad with spaces to ensure we get spaces between words |
|||
# and importantly _around_ punctuation. We want: |
|||
# `<w>Rispuosemi</w>: «<w>Non</w>` and not `<w>Rispuosemi</w>:«<w>Non</w>`. |
|||
new_word = ' ' + starting_punct_chars + '<w>' + middle_word_chars + '</w>' + ending_punct_chars + ' ' |
|||
Cxmltmp.write(new_word) |
|||
Ctxt.close() |
|||
Cxmltmp.close() |
|||
with open(tmpxmlfile,'r') as Cxmltmp: |
|||
# Add space before opening word tag |
|||
def add_space(match): |
|||
match = match.group() |
|||
return re.sub('<w>', ' <w>', match) |
|||
j = 1 |
|||
for line in Cxmltmp: |
|||
# Swap double spaces from new_word with single spaces |
|||
line_spaced = re.sub(' ',' ',line) |
|||
# If there's a single space at the beginning of the line, delete it |
|||
line_spaced = line_spaced.lstrip(' ') |
|||
# Add three tabs and opening line tags at the beginning |
|||
line_tag = '\t\t\t\t\t<l l_num="' + str(j) + '"> ' |
|||
line_spaced = re.sub('^',line_tag,line_spaced) |
|||
# Add closing line tags |
|||
line_spaced = re.sub('\n',' </l>\n',line_spaced) |
|||
Cxml.write(line_spaced) |
|||
j += 1 |
|||
Cxmltmp.close() |
|||
os.remove(tmpxmlfile) |
|||
Cxml.close() |
|||
|
|||
for canto in os.listdir(canto_dir): |
|||
if canto != 'word-tags.py' and canto != '.word-tags.py.swp': |
|||
add_tags(canto) |
|||
if canto.endswith('.txt'): |
|||
os.remove(os.path.join(canto_dir, canto)) |
|||
@ -1,9 +0,0 @@ |
|||
<?xml version="1.0" encoding="UTF-8"?> |
|||
|
|||
<TEI xmlns="http://www.tei-c.org/ns/1.0"> |
|||
<teiHeader> |
|||
<fileDesc> |
|||
<titleStmt>CANTICLE</titleStmt> |
|||
</fileDesc> |
|||
</teiHeader> |
|||
<text> |
|||
@ -1,55 +0,0 @@ |
|||
#!/bin/bash |
|||
|
|||
# A script which converts plaintext cantos from one canticle to XML formatting. |
|||
|
|||
canticles=( 'inferno' 'purgatorio' 'paradiso' ) |
|||
|
|||
comedy_xml_dir=../comedy-xml.d |
|||
comedy_xml_dir_bak=../comedy-xml.d.bak |
|||
comedy_plaintext_dir=../comedy-plaintext.d |
|||
shell_scripts_dir="$(pwd)" |
|||
|
|||
if [[ "$(pwd)" =~ shell-scripts.d ]]; then |
|||
clear |
|||
if [[ ! -d "$comedy_xml_dir" ]]; then |
|||
echo 'Making `comedy-xml.d`' |
|||
mkdir $comedy_xml_dir |
|||
else |
|||
echo 'Moving your `../comedy-xml.d/` to `../comedy-xml.d.bak`' |
|||
mv $comedy_xml_dir $comedy_xml_dir_bak && mkdir $comedy_xml_dir |
|||
fi |
|||
for canticle in "${canticles[@]}"; |
|||
do |
|||
echo -e "\nRenaming dirs..." |
|||
dir="$canticle-txt.d" |
|||
dir_xml="$canticle-xml.d" |
|||
if [[ -d $comedy_plaintext_dir ]]; then |
|||
echo -e "\tMoving $dir to $dir_xml" |
|||
cp -r "$comedy_plaintext_dir/$dir" "$comedy_xml_dir/$dir_xml" |
|||
else |
|||
echo "Could not find dir: $comedy_plaintext_dir" |
|||
fi |
|||
done |
|||
for canticle in "${canticles[@]}"; |
|||
do |
|||
dir_xml="$comedy_xml_dir/$canticle-xml.d" |
|||
echo "Copying word-tags.py" && cp ../py-scripts.d/word-tags.py $dir_xml/word-tags.py &&\ |
|||
echo "Changing dir to $dir_xml" && cd $dir_xml &&\ |
|||
echo "Running word-tags.py" && python3 word-tags.py &&\ |
|||
echo "Removing word-tags.py" && rm word-tags.py &&\ |
|||
echo "Changing dir to $shell_scripts_dir" && cd $shell_scripts_dir &&\ |
|||
echo "Copying tercet-tags.sh" && cp ../shell-scripts.d/tercet-tags.sh $dir_xml/tercet-tags.sh &&\ |
|||
echo "Changing dir to $dir_xml" && cd $dir_xml &&\ |
|||
echo "Running tercet-tags.sh" && ./tercet-tags.sh &&\ |
|||
echo "Removing tercet-tags.sh" && rm tercet-tags.sh &&\ |
|||
echo "Changing dir to $shell_scripts_dir" && cd $shell_scripts_dir &&\ |
|||
echo "Copying top-level-tags.sh" && cp ../shell-scripts.d/top-level-tags.sh $dir_xml/top-level-tags.sh &&\ |
|||
echo "Changing dir to $dir_xml" && cd $dir_xml &&\ |
|||
echo "Running top-level-tags.sh" && ./top-level-tags.sh &&\ |
|||
echo "Removing top-level-tags.sh" && rm top-level-tags.sh &&\ |
|||
echo "Adding .gitignore" && echo 'xpath.sh' > .gitignore &&\ |
|||
echo "Changing dir to $shell_scripts_dir" && cd $shell_scripts_dir |
|||
done |
|||
else |
|||
echo "Wrong directory?" |
|||
fi |
|||
@ -1,25 +0,0 @@ |
|||
#!/bin/bash |
|||
|
|||
# Make full canticle files from comedy-xml.d |
|||
|
|||
xml_dir=../comedy-xml.d |
|||
|
|||
canticles=( 'inferno' 'purgatorio' 'paradiso' ) |
|||
|
|||
for canticle in "${canticles[@]}"; |
|||
do |
|||
canticle_dir="$xml_dir/$canticle-xml.d/" |
|||
canticle_complete=$xml_dir"/$canticle-complete.xml" |
|||
cp ./canticle-base.xml $canticle_complete |
|||
sed -i "s/CANTICLE/The\ Complete\ ${canticle^}/" $canticle_complete |
|||
echo -e "\t\t<$canticle>" >> $canticle_complete |
|||
for canto in $canticle_dir*; |
|||
do |
|||
canto_text="$(xmlstarlet sel -t -c "_:TEI/_:text/_:canto" $canto | sed "s/^/\t/g")" |
|||
echo -e "$canto_text" >> $canticle_complete |
|||
done |
|||
echo -e "\t\t</$canticle>" >> $canticle_complete |
|||
echo -e "\t</text>" >> $canticle_complete |
|||
echo "</TEI>" >> $canticle_complete |
|||
sed -i 's/<canto\ xmlns=\"http:\/\/www.tei-c.org\/ns\/1.0\"/\t\t<canto/g' $canticle_complete |
|||
done |
|||
@ -1,13 +0,0 @@ |
|||
#!/bin/bash |
|||
|
|||
# Rename canto files |
|||
|
|||
for file in *; |
|||
do |
|||
if [[ $file != r.sh ]]; then |
|||
num="$(echo $file | tr -d -c 0-9)" |
|||
pad="$(printf "%03d\n" $num)" |
|||
echo "$file: $pad" |
|||
mv $file "$pad-purgatorio.txt" |
|||
fi |
|||
done |
|||
@ -1,36 +0,0 @@ |
|||
#!/bin/bash |
|||
# Add terzina tags to each canto.xml file in a directory |
|||
# Also add canto number attribute. |
|||
|
|||
echo -e "\nAdding terzina tags and numbers." |
|||
|
|||
for file in *; |
|||
do |
|||
if [[ "$file" != tercet-tags.sh ]] && [[ "$file" != canticle-to-xml.sh ]]; then # exclude this script |
|||
if [[ "$file" != sed* ]]; then # exclude sed file made later |
|||
echo -e "Modifying $file" |
|||
# Every third line (mod 3) add a closing tag, newline, and opening tag. |
|||
# TODO |
|||
# How many tabs to add? |
|||
awk -i inplace '{print}; NR % 3 == 0 {print "\t\t\t\t</tercet>\n\t\t\t\t<tercet t_num=~NUM~>"}' "$file" |
|||
# Add an opening tag at the beginning and a closing tag at the end because the above awk doesn't. |
|||
sed -i '1s/^/\t\t\t\t<tercet t_num="1">\n/' "$file" |
|||
# Also remove the newline at the end of the file. |
|||
sed -i '$ d' "$file" |
|||
echo -e "\t\t\t\t</tercet>" >> "$file" |
|||
# Add the canto number attribute (at most 160/3 ~ 54 terzine) |
|||
for i in $(seq 1 54); |
|||
do |
|||
# Substitute in the actual number with sed. I couldn't figure out |
|||
# how to include the $i variable with the surrounding attribute |
|||
# quotes in the awk statement, so I just used sed here separately. |
|||
|
|||
# We start at i=2 because the awk command above |
|||
# doesn't add a terzina tag to the first terzina. |
|||
TERZ_NUM=$((i + 1)) |
|||
# Replace only first occurence of ~NUM~. |
|||
sed -i -e "0,/~NUM~/ s/~NUM~/\"$TERZ_NUM\"/" "$file" |
|||
done |
|||
fi |
|||
fi |
|||
done |
|||
@ -1,49 +0,0 @@ |
|||
#!/bin/bash |
|||
|
|||
# This script adds top-level tags to your XML files. |
|||
# - XML header |
|||
# - TEI header |
|||
|
|||
echo -e "\nAdding top-level tags." |
|||
|
|||
for file in *; |
|||
do |
|||
if [[ "$file" != 'top-level-tags.sh' ]] && [[ "$file" != 'canticle-to-xml.sh' ]]; then |
|||
ZEROS_CANTO_NUM="$(echo "'$file'" | tr -d -c 0-9)" # get canto number |
|||
#CANTO_NUM="$(echo $ZEROS_CANTO_NUM | tr -d 0)" |
|||
CANTO_NUM=$((10#$ZEROS_CANTO_NUM)) |
|||
if [[ "$file" == *inferno* ]]; then |
|||
CANTICLE="Inferno" |
|||
COMM_NUM="$CANTO_NUM" # same as inferno canto number |
|||
elif [[ "$file" == *purgatorio* ]]; then |
|||
CANTICLE="Purgatorio" |
|||
COMM_NUM="$(($CANTO_NUM + 34))" # add 34 if in purgatory |
|||
elif [[ "$file" == *paradiso* ]]; then |
|||
CANTICLE="Paradiso" |
|||
COMM_NUM="$(($CANTO_NUM + 67))" # add 68 if in paradise |
|||
else |
|||
echo -e "\nWhat file is this? $file" |
|||
fi |
|||
# Add tags to first line of file |
|||
sed -i -e '1s/^/<?xml version="1.0" encoding="UTF-8"?>\ |
|||
\n<TEI xmlns="http:\/\/www.tei-c.org\/ns\/1.0">\ |
|||
\t<teiHeader>\ |
|||
\t\t<fileDesc>\ |
|||
\t\t\t<titleStmt>Canto ~TITLE_CANTO_NUM~ of ~CANTICLE~<\/titleStmt>\ |
|||
\t\t<\/fileDesc>\ |
|||
\t<\/teiHeader>\ |
|||
\t<text>\ |
|||
\t\t<canto canto_num=~CANTO_NUM~ comm_num=~COMM_NUM~>\ |
|||
\t\t\t<tercets>\n/' "$file" |
|||
# Replace canto number, comedy number, and canticle |
|||
sed -i -e "s/~TITLE_CANTO_NUM~/$CANTO_NUM/" "$file" |
|||
sed -i -e "s/~CANTO_NUM~/\"$CANTO_NUM\"/" "$file" |
|||
sed -i -e "s/~COMM_NUM~/\"$COMM_NUM\"/" "$file" |
|||
sed -i -e "s/~CANTICLE~/$CANTICLE/" "$file" |
|||
# Add tags to end of file |
|||
echo -e "\t\t\t</tercets>" >> "$file" |
|||
echo -e "\t\t</canto>" >> "$file" |
|||
echo -e "\t</text>" >> "$file" |
|||
echo -e "</TEI>" >> "$file" |
|||
fi |
|||
done |
|||
@ -1,71 +0,0 @@ |
|||
#!/bin/bash |
|||
|
|||
# An interactive xpath query commandline tool. |
|||
# Stores your previous query to reduce typing. |
|||
|
|||
# File for previous query |
|||
touch .prev-xpath.tmp |
|||
if [[ ! -e ".gitignore" ]]; then |
|||
echo 'xpath.sh' > .gitignore |
|||
fi |
|||
|
|||
# Colored output |
|||
GREEN='\033[0;32m' |
|||
NC='\033[0m' # no color |
|||
|
|||
# Ask for canto file |
|||
clear |
|||
read -p "Choose a canto: [i,r,p][1-34] " CANTO |
|||
canticle="$(echo $CANTO | tr -d -c a-z)" |
|||
canto_num="$(echo $CANTO | tr -d -c 0-9)" |
|||
pad_num="$(printf "%03d\n" $canto_num)" |
|||
|
|||
# Create complete filename |
|||
if [[ "$canticle" == 'i' ]]; then |
|||
canticle='Inferno' |
|||
file="$pad_num-inferno-petrocchi.xml" |
|||
echo $file |
|||
elif [[ "$canticle" == 'r' ]]; then |
|||
canticle='Purgatorio' |
|||
file="$pad_num-purgatorio-petrocchi.xml" |
|||
elif [[ "$canticle" == 'p' ]]; then |
|||
canticle='Paradiso' |
|||
file="$pad_num-paradiso-petrocchi.xml" |
|||
else |
|||
echo "Not a valid canto file: $file" |
|||
fi |
|||
|
|||
# Start interactive query |
|||
if [[ -e "$file" ]]; then |
|||
clear && echo -e "You are searching ${canticle^} ${CANTO_NUM}.\nAdd a trailing slash ${GREEN}\`/\`${NC} to your search before submitting it. The default first two search choices are ${GREEN}\`canto\`${NC} and then ${GREEN}\`terzine\`${NC}. Press ${GREEN}<enter>${NC} for those defaults and type something else to search that.\n" |
|||
read -p "Load previous: (Y)/n " PREV |
|||
case "$PREV" in |
|||
N|n) |
|||
search='' |
|||
;; |
|||
Y|y|*) |
|||
search="$(cat .prev-xpath.tmp)" |
|||
;; |
|||
esac |
|||
i='0' |
|||
# Start while loop for the query. Break the loop if the query ends with a slash `/`. |
|||
while true; do |
|||
read -e -i "$search" -p "$(echo -e "\nSearch: \n "${GREEN}"===> "${NC})" nsearch |
|||
if [[ "${nsearch: -1}" == / ]]; then # if last char trailing slash then search |
|||
path="${nsearch::-1}" # remove trailing slash |
|||
echo "$path" > .prev-xpath.tmp # store query for next time |
|||
# perform the search (requires `xmlstarlet` and `bat` pager) |
|||
xmlstarlet sel -t -v "$path" $file | batcat -l xml |
|||
exit |
|||
elif [[ "$i" == 0 ]] && [[ "$nsearch" == '' ]]; then # load '/TEI/text' query on first loop |
|||
search="_:TEI/_:text/_:" |
|||
elif [[ "$nsearch" == '_:TEI/_:text/_:' ]]; then # load '/TEI/text/canto/tercets' on second loop |
|||
search="_:TEI/_:text/_:canto/_:tercets/_:" |
|||
else |
|||
search="${nsearch}" # else keep search the same |
|||
fi |
|||
i=$[$i+1] |
|||
done |
|||
else |
|||
echo "Canto file not found. What directory are you in?" |
|||
fi |
|||
Loading…
Reference in new issue