ikat 0.12.0

Weave Markdown into camera-ready LaTeX: mermaid-to-TikZ, pgfplots figures, publisher templates
Documentation 
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

"""Token inventory over every `$$...$$` display span in the exported corpus."""
import re, collections
from pathlib import Path

spans = []
for md in sorted(Path(__file__).resolve().parent.joinpath('full').glob('*/*.md')):
    txt = md.read_text(encoding='utf-8', errors='replace')
    for m in re.finditer(r'^\$\$(.+)\$\$\s*$', txt, re.M):
        spans.append(m.group(1))
print('spans:', len(spans))

cmds = collections.Counter()
for s in spans:
    for m in re.finditer(r'\\([a-zA-Z]+)', s):
        cmds[m.group(1)] += 1
print('lettered commands:', len(cmds))
for c, n in cmds.most_common(200):
    print(f'  {c:24s} {n}')

na = collections.Counter()
for s in spans:
    for c in s:
        if ord(c) > 127:
            na[c] += 1
print('non-ascii:', {c: n for c, n in na.most_common()})

two = collections.Counter()
for s in spans:
    for m in re.finditer(r'\\([^a-zA-Z])', s):
        two[m.group(1)] += 1
print('punct commands:', dict(two))