brianr/SM2Gen
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Sort formatting for english lex and add localise to tables columns

Browse Source
This commit is contained in:
Brian Read
2024-05-05 09:31:10 +01:00
parent 145c45f483
commit 228a42ed60
8 changed files with 103 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files

59
sm2gen.py
View File

@@ -11,7 +11,7 @@ import pkg_resources
from datetime import datetime
import xml.etree.ElementTree as ET
SME2Gen_version = '0.6'
SME2Gen_version = '0.7'
json5_dict: dict = {}
json5_html_list: list = []
@@ -181,6 +181,52 @@ def get_db_fields():
def get_table_control_data():
return find_values_with_key(json5_html_list,'TableControl')
def format_text(text):
#
# Turn a piece of text into something a bit better formatted - spaces after full stop and comma and also capitalise sentences
#
# Create a list to hold the formatted sentences
formatted_sentences = []
# Split the text into sentences
sentences = text.split(".")
words = sentences[0].split(" ")
#print(len(sentences))
# Deal with one capitalised word
if sentences[0].isupper() and len(sentences) == 1 and len(words) == 1:
return sentences[0].capitalize()
else:
for sentence in sentences:
#print(sentence)
# and splt into sub phrases, based on comma
formatted_phrases = []
phrases = sentence.split(",")
for phrase in phrases:
#print(phrase)
phrase = phrase.lstrip()
formatted_words = []
words = phrase.split(' ')
for i,word in enumerate(words):
#print(i,word)
# Check if the word is fully uppercase or not the first
word = word.lstrip()
if word.isupper() or i != 0:
formatted_words.append(word)
else:
# Capitalize the word
formatted_words.append(word.capitalize())
# Join the formatted words back together for this phrase
formatted_phrase = ' '.join(formatted_words).lstrip()
formatted_phrases.append(formatted_phrase)
# and sentence
formatted_sentence = ", ".join(formatted_phrases).lstrip()
formatted_sentences.append(formatted_sentence)
# Join the formatted sentences back together
formatted_text = ". ".join(formatted_sentences).lstrip()
return formatted_text
if __name__ == "__main__":
try:
chameleon_version = pkg_resources.get_distribution("Chameleon").version
@@ -385,18 +431,22 @@ if __name__ == "__main__":
# Map all spaces to "_" on left hand side
# amd truncate it to max five words
original_str = lex_message
if lex_message.startswith(hl('prefix')):
# Checkif it starts with the prefix (any case|)
if lex_message.lower().startswith(hl('prefix').lower()):
left_str = lex_message
right_str = lex_message[len(hl('prefix'))+1:]
# And take out any "_", map to " "
else:
left_str = hl('prefix')+"_"+lex_message
right_str = lex_message
right_str = right_str.replace("_"," ")
right_str = format_text(right_str)
left_str = left_str.replace(" ","_")
words = left_str.split('_')[:6]
left_str = "_".join(words)
next_lex_str = {"orig":original_str,"left":left_str,"right":right_str}
string_lib.append(next_lex_str)
print(string_lib)
#print(string_lib)
#And write it to lex file
# Now process them one by one into the lexical file
lex_all = "";
@@ -406,6 +456,7 @@ if __name__ == "__main__":
with open( lex_file, 'w') as file:
file.write(lex_all)
#and then play the strings back into the partials and the layout file
print("..and feed the lex string names back into other files")
for filename in all_files:
with open(filename, 'r') as file:
file_content = file.read()
@@ -414,12 +465,12 @@ if __name__ == "__main__":
original_str = item["orig"]
left_str = item["left"]
right_str = item["right"]
# Replace all occurrences of original string with left string in 'contents'
file_content = file_content.replace(original_str, left_str)
# and write it back
with open(filename, 'w') as file:
file.write(file_content)
print(f"Write out modified:{filename}")