File size: 5,381 Bytes
f763e99 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 |
from docx import Document
import os
import sys
import languages
def docx_replace(doc, data):
paragraphs = list(doc.paragraphs)
for t in doc.tables:
for row in t.rows:
for cell in row.cells:
for paragraph in cell.paragraphs:
paragraphs.append(paragraph)
for key, val in data.items():
for p in paragraphs:
#key_name = '${{{}}}'.format(key) # I'm using placeholders in the form ${PlaceholderName}
key_name = key
if key_name in p.text:
#print(f'old one {p.text}')
inline = p.runs
# Replace strings and retain the same style.
# The text to be replaced can be split over several runs so
# search through, identify which runs need to have text replaced
# then replace the text in those identified
started = False
key_index = 0
# found_runs is a list of (inline index, index of match, length of match)
found_runs = list()
found_all = False
replace_done = False
for i in range(len(inline)):
# case 1: found in single run so short circuit the replace
if key_name in inline[i].text and not started:
found_runs.append((i, inline[i].text.find(key_name), len(key_name)))
text = inline[i].text.replace(key_name, str(val))
inline[i].text = text
replace_done = True
found_all = True
break
if key_name[key_index] not in inline[i].text and not started:
# keep looking ...
continue
# case 2: search for partial text, find first run
if key_name[key_index] in inline[i].text and inline[i].text[-1] in key_name and not started:
# check sequence
start_index = inline[i].text.find(key_name[key_index])
check_length = len(inline[i].text)
for text_index in range(start_index, check_length):
if inline[i].text[text_index] != key_name[key_index]:
# no match so must be false positive
break
if key_index == 0:
started = True
chars_found = check_length - start_index
key_index += chars_found
found_runs.append((i, start_index, chars_found))
if key_index != len(key_name):
continue
else:
# found all chars in key_name
found_all = True
break
# case 2: search for partial text, find subsequent run
if key_name[key_index] in inline[i].text and started and not found_all:
# check sequence
chars_found = 0
check_length = len(inline[i].text)
for text_index in range(0, check_length):
if inline[i].text[text_index] == key_name[key_index]:
key_index += 1
chars_found += 1
else:
break
# no match so must be end
found_runs.append((i, 0, chars_found))
if key_index == len(key_name):
found_all = True
break
if found_all and not replace_done:
for i, item in enumerate(found_runs):
index, start, length = [t for t in item]
if i == 0:
text = inline[index].text.replace(inline[index].text[start:start + length], str(val))
inline[index].text = text
else:
text = inline[index].text.replace(inline[index].text[start:start + length], '')
inline[index].text = text
#print(p.text)
def translate_fill(document_name,output_file, src, trg):
template_document = Document(document_name)
variables = {}
for paragraph in template_document.paragraphs:
if(paragraph.text.strip() != ""):
variables[paragraph.text] = languages(paragraph.text, src, trg)
for t in template_document.tables:
for row in t.rows:
for cell in row.cells:
for paragraph in cell.paragraphs:
if(paragraph.text.strip() != ""):
variables[paragraph.text] = languages(paragraph.text, src, trg)
docx_replace(template_document, variables)
template_document.save(output_file)
return variables
sys.modules[__name__] = translate_fill
## args = translate_fill(document_name, output_name, src, trg) |