Regex

101:02:10.3 
2a: Lorem ipsum dolor sit amet,  
3b: consectetur adipiscing elit.
4a: Mauris a turpis erat. 
501:02:20.4 
6a: Vivamus dignissim aliquam
7b: Nam ultricies
8(etc.)
9+---+--------------------+---------------------------------+
10|   |         A          |                B                |
11+---+--------------------+---------------------------------+
12| 1 | 01:02:10.3         | a: Lorem ipsum dolor sit amet,  |
13| 2 |                    | b: consectetur adipiscing elit. |
14| 3 |                    | a: Mauris a turpis erat.        |
15| 4 | ------------------ | ------------------------------- |
16| 5 | 01:02:20.4         | a: Vivamus dignissim aliqua     |
17| 6 |                    | b: Nam ultricies                |
18+---+--------------------+---------------------------------+
19IS_BOLD = { 
20    'a': True
21    'b': False
22}
23
24row_cells = table.add_row().cells
25
26for line in lines: 
27    if is_timestamp(line): # function that uses regex to discern between columns
28        if row_cells[1]:
29            row_cells = table.add_row().cells
30
31        row_cells[0].text = line
32
33    else 
34        row_cells[1].text += line
35
36        if IS_BOLD[ line.split(":")[0] ]:
37            # make only this line within the cell bold, somehow.
38from docx import Document
39from docx.shared import Inches
40import os
41import re
42
43
44def is_timestamp(line):
45    # it's flaky, I saw you have your own method and probably you did a better job parsing this.
46    return re.match(r'^\d{2}:\d{2}:\d{2}', line) is not None
47
48
49def parse_raw_script(raw_script):
50    current_timestamp = ''
51    current_content = ''
52    for line in raw_script.splitlines():
53        line = line.strip()
54        if is_timestamp(line):
55            if current_timestamp:
56                yield {
57                    'timestamp': current_timestamp,
58                    'content': current_content
59                }
60
61            current_timestamp = line
62            current_content = ''
63            continue
64
65        if current_content:
66            current_content += '\n'
67
68        current_content += line
69
70    if current_timestamp:
71        yield {
72            'timestamp': current_timestamp,
73            'content': current_content
74        }
75
76
77def should_bold(line):
78    # i leave it to you to replace with your logic
79    return line.startswith('a:')
80
81
82def load_raw_script():
83    # I placed here the example from your question. read from file instead I presume
84
85    return '''01:02:10.3 
86a: Lorem ipsum dolor sit amet,  
87b: consectetur adipiscing elit.
88a: Mauris a turpis erat. 
8901:02:20.4 
90a: Vivamus dignissim aliquam
91b: Nam ultricies'''
92
93
94def convert_raw_script_to_docx(raw_script, output_file_path):
95    document = Document()
96    table = document.add_table(rows=1, cols=3, style="Table Grid")
97
98    # add header row
99    header_row = table.rows[0]
100    header_row.cells[0].text = ''
101    header_row.cells[1].text = 'A'
102    header_row.cells[2].text = 'B'
103
104    # parse the raw script into something iterable
105    script_rows = parse_raw_script(raw_script)
106
107    # create a row for each timestamp row
108    for script_row in script_rows:
109        timestamp = script_row['timestamp']
110        content = script_row['content']
111
112        row = table.add_row()
113        timestamp_cell = row.cells[1]
114        timestamp_cell.text = timestamp
115
116        content_cell = row.cells[2]
117        content_paragraph = content_cell.paragraphs[0]  # using the cell's default paragraph here instead of creating one
118
119        for line in content.splitlines():
120            run = content_paragraph.add_run(line)
121            if should_bold(line):
122                run.bold = True
123
124            run.add_break()
125
126    # resize table columns (optional)
127    for row in table.rows:
128        row.cells[0].width = Inches(0.2)
129        row.cells[1].width = Inches(1.9)
130        row.cells[2].width = Inches(3.9)
131
132    document.save(output_file_path)
133
134
135def main():
136    script_dir = os.path.dirname(__file__)
137    dist_dir = os.path.join(script_dir, 'dist')
138
139    if not os.path.isdir(dist_dir):
140        os.makedirs(dist_dir)
141
142    output_file_path = os.path.join(dist_dir, 'so-template.docx')
143    raw_script = load_raw_script()
144    convert_raw_script_to_docx(raw_script, output_file_path)
145
146
147if __name__ == '__main__':
148    main()
149
150

101:02:10.3 
2a: Lorem ipsum dolor sit amet,  
3b: consectetur adipiscing elit.
4a: Mauris a turpis erat. 
501:02:20.4 
6a: Vivamus dignissim aliquam
7b: Nam ultricies
8(etc.)
9+---+--------------------+---------------------------------+
10|   |         A          |                B                |
11+---+--------------------+---------------------------------+
12| 1 | 01:02:10.3         | a: Lorem ipsum dolor sit amet,  |
13| 2 |                    | b: consectetur adipiscing elit. |
14| 3 |                    | a: Mauris a turpis erat.        |
15| 4 | ------------------ | ------------------------------- |
16| 5 | 01:02:20.4         | a: Vivamus dignissim aliqua     |
17| 6 |                    | b: Nam ultricies                |
18+---+--------------------+---------------------------------+
19IS_BOLD = { 
20    'a': True
21    'b': False
22}
23
24row_cells = table.add_row().cells
25
26for line in lines: 
27    if is_timestamp(line): # function that uses regex to discern between columns
28        if row_cells[1]:
29            row_cells = table.add_row().cells
30
31        row_cells[0].text = line
32
33    else 
34        row_cells[1].text += line
35
36        if IS_BOLD[ line.split(":")[0] ]:
37            # make only this line within the cell bold, somehow.
38from docx import Document
39from docx.shared import Inches
40import os
41import re
42
43
44def is_timestamp(line):
45    # it's flaky, I saw you have your own method and probably you did a better job parsing this.
46    return re.match(r'^\d{2}:\d{2}:\d{2}', line) is not None
47
48
49def parse_raw_script(raw_script):
50    current_timestamp = ''
51    current_content = ''
52    for line in raw_script.splitlines():
53        line = line.strip()
54        if is_timestamp(line):
55            if current_timestamp:
56                yield {
57                    'timestamp': current_timestamp,
58                    'content': current_content
59                }
60
61            current_timestamp = line
62            current_content = ''
63            continue
64
65        if current_content:
66            current_content += '\n'
67
68        current_content += line
69
70    if current_timestamp:
71        yield {
72            'timestamp': current_timestamp,
73            'content': current_content
74        }
75
76
77def should_bold(line):
78    # i leave it to you to replace with your logic
79    return line.startswith('a:')
80
81
82def load_raw_script():
83    # I placed here the example from your question. read from file instead I presume
84
85    return '''01:02:10.3 
86a: Lorem ipsum dolor sit amet,  
87b: consectetur adipiscing elit.
88a: Mauris a turpis erat. 
8901:02:20.4 
90a: Vivamus dignissim aliquam
91b: Nam ultricies'''
92
93
94def convert_raw_script_to_docx(raw_script, output_file_path):
95    document = Document()
96    table = document.add_table(rows=1, cols=3, style="Table Grid")
97
98    # add header row
99    header_row = table.rows[0]
100    header_row.cells[0].text = ''
101    header_row.cells[1].text = 'A'
102    header_row.cells[2].text = 'B'
103
104    # parse the raw script into something iterable
105    script_rows = parse_raw_script(raw_script)
106
107    # create a row for each timestamp row
108    for script_row in script_rows:
109        timestamp = script_row['timestamp']
110        content = script_row['content']
111
112        row = table.add_row()
113        timestamp_cell = row.cells[1]
114        timestamp_cell.text = timestamp
115
116        content_cell = row.cells[2]
117        content_paragraph = content_cell.paragraphs[0]  # using the cell's default paragraph here instead of creating one
118
119        for line in content.splitlines():
120            run = content_paragraph.add_run(line)
121            if should_bold(line):
122                run.bold = True
123
124            run.add_break()
125
126    # resize table columns (optional)
127    for row in table.rows:
128        row.cells[0].width = Inches(0.2)
129        row.cells[1].width = Inches(1.9)
130        row.cells[2].width = Inches(3.9)
131
132    document.save(output_file_path)
133
134
135def main():
136    script_dir = os.path.dirname(__file__)
137    dist_dir = os.path.join(script_dir, 'dist')
138
139    if not os.path.isdir(dist_dir):
140        os.makedirs(dist_dir)
141
142    output_file_path = os.path.join(dist_dir, 'so-template.docx')
143    raw_script = load_raw_script()
144    convert_raw_script_to_docx(raw_script, output_file_path)
145
146
147if __name__ == '__main__':
148    main()
149
150IS_BOLD = {
151    'a': True,
152    'b': False
153}
154
155row_cells = table.add_row().cells
156
157for line in lines:
158    if is_timestamp(line):
159        if row_cells[1]:
160            row_cells = table.add_row().cells
161        row_cells[0].text = line
162
163    else:
164        run = row_cells[1].paragraphs[0].add_run(line)
165        if IS_BOLD[line.split(":")[0]]:
166            run.bold = True
167
168        run.add_break()
169

1/./s
2

1/./s
2Unsupported use of /s.  In Raku please use: .  or \N.
3

1/./s
2Unsupported use of /s.  In Raku please use: .  or \N.
3/\Qfoo\E/
4

1/./s
2Unsupported use of /s.  In Raku please use: .  or \N.
3/\Qfoo\E/
4Unsupported use of \Q as quotemeta.  In Raku please use: quotes or
5literal variable match.
6

1> 'abefo' ~~ /a [(b) | (c) (d)] (e)[(f)|(g)]/
2｢abef｣
3 0 => ｢b｣
4 2 => ｢e｣
5 3 => ｢f｣
6 $0 = 'b'
7 $1 = undef
8 $2 = undef 
9 $3 = e
10 $4 = f
11/ a [ (b) | (c) (d) ] $3=(e) [ (f) | (g) ] /
12
13andthen say 'abefo' ~~ $_
14
15｢abef｣
16 0 => ｢b｣
17 3 => ｢e｣
18 4 => ｢f｣
19

1#!/usr/bin/perl
2
3use strict;
4use warnings;
5
6'12' =~ /(?<foo>\d)(?<foo>\d)/; # '1' and '2' will be captured individually
7
8print $+{'foo'}, "\n";          # prints '1'
9
10for (@{$-{'foo'}}) {            # $-{'foo'} is a reference to an array
11    print $_, "\n";             # prints '1' and '2'
12}
13

1code fx         category
2AXD  AXDG.R     cat1
3AXF  AXDG_e.FE  cat1 
4333  333.R      cat1
5....
6code    fx         category
7AXD.R   AXDG.R     cat1
8AXF.FE  AXDG_e.FE  cat1
9333.R   333.R      cat1
10.....
11df.loc[df['category']== 'cat1', 'code'] = df[df['category'] == 'cat1']['code'].str.replace(r'[a-z](?=\.)', '', regex=True).str.replace(r'_?(?=\.)','', regex=True).str.replace(r'G(?=\.)', '', regex=True)
12>>> df['code'] = df['code'] + '.' + df['fx'].str.split(pat=".", expand=True)[1]
13>>> df
14    code    fx          category    
150   AXD.R   AXDG.R      cat1        
161   AXF.FE  AXDG_e.FE   cat1        
172   333.R   333.R       cat1    
18

1code fx         category
2AXD  AXDG.R     cat1
3AXF  AXDG_e.FE  cat1 
4333  333.R      cat1
5....
6code    fx         category
7AXD.R   AXDG.R     cat1
8AXF.FE  AXDG_e.FE  cat1
9333.R   333.R      cat1
10.....
11df.loc[df['category']== 'cat1', 'code'] = df[df['category'] == 'cat1']['code'].str.replace(r'[a-z](?=\.)', '', regex=True).str.replace(r'_?(?=\.)','', regex=True).str.replace(r'G(?=\.)', '', regex=True)
12>>> df['code'] = df['code'] + '.' + df['fx'].str.split(pat=".", expand=True)[1]
13>>> df
14    code    fx          category    
150   AXD.R   AXDG.R      cat1        
161   AXF.FE  AXDG_e.FE   cat1        
172   333.R   333.R       cat1    
18>>> df['code'] = (df['code'] + '.' + df['fx'].str.split(pat=".", expand=True)[1]).where(df['category'].eq("cat1"), df['code'])
19

1ABC1000000 - valid
23212130000 - valid
30000000000 - valid
4ABC1000100 - invalid
50001000000 - invalid
6^(?=[A-Z0-9]{10}$)[A-Z1-9]*0+$
7

1ABC1000000 - valid
23212130000 - valid
30000000000 - valid
4ABC1000100 - invalid
50001000000 - invalid
6^(?=[A-Z0-9]{10}$)[A-Z1-9]*0+$
7^(?=[A-Z0-9]{10}$)[^0]*0*$
8

1ABC1000000 - valid
23212130000 - valid
30000000000 - valid
4ABC1000100 - invalid
50001000000 - invalid
6^(?=[A-Z0-9]{10}$)[A-Z1-9]*0+$
7^(?=[A-Z0-9]{10}$)[^0]*0*$
8const regex = /^(?=[A-Z0-9]{10}$)[^0]*0*$/;
9["ABC1000000", "3212130000", "0000000000", "ABC1000100", "0001000000"]
10.forEach(s =>
11  console.log(`${s} --> ${regex.test(s)}`)
12);

1ABC1000000 - valid
23212130000 - valid
30000000000 - valid
4ABC1000100 - invalid
50001000000 - invalid
6^(?=[A-Z0-9]{10}$)[A-Z1-9]*0+$
7^(?=[A-Z0-9]{10}$)[^0]*0*$
8const regex = /^(?=[A-Z0-9]{10}$)[^0]*0*$/;
9["ABC1000000", "3212130000", "0000000000", "ABC1000100", "0001000000"]
10.forEach(s =>
11  console.log(`${s} --> ${regex.test(s)}`)
12);^(?:[A-Z1-9]*0+[A-Z1-9]|([A-Z0-9]{10})$)
13

1foo a b c
2foo b c a
3foo a b
4foo b
5foo b b
6^foo((?!.*\1) [abc])+$
7

1foo a b c
2foo b c a
3foo a b
4foo b
5foo b b
6^foo((?!.*\1) [abc])+$
7^foo(?!.* ([abc]).*\1)(?: [abc])+$
8