Forked from adejones/python-docx-replace-text-and-retain-style.py
Last active
May 6, 2020 16:51
-
-
Save RoelTim/a8412f7605b536f181b65ba7a3048034 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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 p in paragraphs: | |
for key, val in data.items(): | |
key_name = '${{{}}}'.format(key) # use placeholders in the form ${PlaceholderName} | |
if key_name in 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) | |
#final check: report the replacement of certain strings failed | |
for t in docu.tables: | |
for row in t.rows: | |
for cell in row.cells: | |
for paragraph in cell.paragraphs: | |
paragraphs.append(paragraph) | |
i=0 #i is the number of replacements that failed | |
for key,val in data.items(): | |
for p in paragraphs: | |
if key in p.text: | |
if i==0: #the first time a missing tag was found | |
print('It seems that something went wrong and not all the strings were replaced. Check for the following string(s):') | |
i=i+1 | |
print('string ',i,': ',key) | |
# usage | |
doc = docx.Document('path/to/template.docx') | |
docx_replace(doc, dict(ItemOne='replacement text', ItemTwo="Some replacement text\nand some more") | |
doc.save('path/to/destination.docx') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment