Spaces:
Sleeping
Sleeping
Claude commited on
Unify the two caps tools' acronym lists
Browse filesconvert_caps (KEEP_WORDS) and replace_allcaps_pptx (PRESERVE_UPPERCASE) each
carried their own hardcoded acronym list, and they had drifted: e.g. "WCAG"
was preserved by replace_allcaps but mangled to "Wcag" by convert_caps when it
appeared as caps *formatting*. Both now load one shared source of truth,
tools/pptx/acronyms.txt (loaded relative to __file__, so it works for the CLI,
the run.py launcher, and the web app's importlib loading). convert_caps uses
the canonical casing; replace_allcaps uses the uppercased forms.
Verified: lists agree (72 entries), WCAG with caps formatting now stays WCAG,
and the smoke test passes 7/7.
- tools/pptx/acronyms.txt +80 -0
- tools/pptx/convert_caps.py +20 -13
- tools/pptx/replace_allcaps_pptx.py +17 -7
tools/pptx/acronyms.txt
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Canonical acronym / abbreviation list β the single source of truth shared by
|
| 2 |
+
# convert_caps.py and replace_allcaps_pptx.py so the two tools can't drift apart.
|
| 3 |
+
#
|
| 4 |
+
# One token per line, in its preferred casing (e.g. "iOS", "PhD", "APIs").
|
| 5 |
+
# - convert_caps restores this exact casing after title-casing.
|
| 6 |
+
# - replace_allcaps compares against the UPPERCASED form to keep matches as-is.
|
| 7 |
+
# Lines starting with '#' and blank lines are ignored; '#' also ends a line.
|
| 8 |
+
|
| 9 |
+
ADA
|
| 10 |
+
AI
|
| 11 |
+
API
|
| 12 |
+
APIs
|
| 13 |
+
ARIA
|
| 14 |
+
AWS
|
| 15 |
+
CEO
|
| 16 |
+
CFO
|
| 17 |
+
CIO
|
| 18 |
+
COO
|
| 19 |
+
CSS
|
| 20 |
+
CSV
|
| 21 |
+
CTO
|
| 22 |
+
DB
|
| 23 |
+
DevOps
|
| 24 |
+
DNS
|
| 25 |
+
EU
|
| 26 |
+
FAQ
|
| 27 |
+
FBI
|
| 28 |
+
GPU
|
| 29 |
+
GPUs
|
| 30 |
+
HR
|
| 31 |
+
HTML
|
| 32 |
+
HTTP
|
| 33 |
+
HTTPS
|
| 34 |
+
I
|
| 35 |
+
ID
|
| 36 |
+
IDs
|
| 37 |
+
IoT
|
| 38 |
+
IP
|
| 39 |
+
ISO
|
| 40 |
+
IT
|
| 41 |
+
iOS
|
| 42 |
+
JAWS
|
| 43 |
+
JSON
|
| 44 |
+
KPI
|
| 45 |
+
KPIs
|
| 46 |
+
LLC
|
| 47 |
+
MBA
|
| 48 |
+
ML
|
| 49 |
+
MVP
|
| 50 |
+
NASA
|
| 51 |
+
NDA
|
| 52 |
+
NVDA
|
| 53 |
+
OKR
|
| 54 |
+
OKRs
|
| 55 |
+
OS
|
| 56 |
+
PDF
|
| 57 |
+
PhD
|
| 58 |
+
PIN
|
| 59 |
+
PR
|
| 60 |
+
QA
|
| 61 |
+
ROI
|
| 62 |
+
SaaS
|
| 63 |
+
SDK
|
| 64 |
+
SEO
|
| 65 |
+
SQL
|
| 66 |
+
SSD
|
| 67 |
+
SSO
|
| 68 |
+
UI
|
| 69 |
+
UK
|
| 70 |
+
URL
|
| 71 |
+
URLs
|
| 72 |
+
US
|
| 73 |
+
USA
|
| 74 |
+
USB
|
| 75 |
+
UX
|
| 76 |
+
VPAT
|
| 77 |
+
VPN
|
| 78 |
+
WAI
|
| 79 |
+
WCAG
|
| 80 |
+
XML
|
tools/pptx/convert_caps.py
CHANGED
|
@@ -15,7 +15,8 @@ Batch (2+ files): saves each to <input>_mixed_case.pptx, or into --outdir
|
|
| 15 |
|
| 16 |
The --keep flag adds extra words that should keep their casing. A built-in
|
| 17 |
list of common acronyms is always applied (AI, API, CEO, etc.). Edit the
|
| 18 |
-
|
|
|
|
| 19 |
|
| 20 |
Requirements:
|
| 21 |
pip install python-pptx
|
|
@@ -30,18 +31,24 @@ from lxml import etree
|
|
| 30 |
from pptx import Presentation
|
| 31 |
|
| 32 |
# ββ Acronyms / words to preserve ββββββββββββββββββββββββββββββββ
|
| 33 |
-
# These words
|
| 34 |
-
#
|
| 35 |
-
#
|
| 36 |
-
|
| 37 |
-
"
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
|
| 41 |
-
|
| 42 |
-
|
| 43 |
-
|
| 44 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
|
| 46 |
# PowerPoint XML namespace for drawingML
|
| 47 |
_nsmap = {"a": "http://schemas.openxmlformats.org/drawingml/2006/main"}
|
|
|
|
| 15 |
|
| 16 |
The --keep flag adds extra words that should keep their casing. A built-in
|
| 17 |
list of common acronyms is always applied (AI, API, CEO, etc.). Edit the
|
| 18 |
+
shared acronyms.txt (next to this script) to permanently add or remove entries
|
| 19 |
+
β replace_allcaps_pptx.py reads the same file.
|
| 20 |
|
| 21 |
Requirements:
|
| 22 |
pip install python-pptx
|
|
|
|
| 31 |
from pptx import Presentation
|
| 32 |
|
| 33 |
# ββ Acronyms / words to preserve ββββββββββββββββββββββββββββββββ
|
| 34 |
+
# These words keep their exact casing after title-case conversion. The list
|
| 35 |
+
# is loaded from the shared acronyms.txt so it stays in sync with
|
| 36 |
+
# replace_allcaps_pptx.py β edit that file to add or remove entries.
|
| 37 |
+
def _load_keep_words() -> set:
|
| 38 |
+
"""Read the canonical acronym list shared with replace_allcaps_pptx.py."""
|
| 39 |
+
path = Path(__file__).resolve().parent / "acronyms.txt"
|
| 40 |
+
words = set()
|
| 41 |
+
try:
|
| 42 |
+
for line in path.read_text(encoding="utf-8").splitlines():
|
| 43 |
+
token = line.split("#", 1)[0].strip()
|
| 44 |
+
if token:
|
| 45 |
+
words.add(token)
|
| 46 |
+
except OSError:
|
| 47 |
+
pass
|
| 48 |
+
return words
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
KEEP_WORDS = _load_keep_words()
|
| 52 |
|
| 53 |
# PowerPoint XML namespace for drawingML
|
| 54 |
_nsmap = {"a": "http://schemas.openxmlformats.org/drawingml/2006/main"}
|
tools/pptx/replace_allcaps_pptx.py
CHANGED
|
@@ -20,13 +20,23 @@ from pptx.util import Pt
|
|
| 20 |
|
| 21 |
|
| 22 |
# ββ Acronyms / abbreviations to KEEP uppercase ββββββββββββββββββββββ
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
"
|
| 27 |
-
|
| 28 |
-
|
| 29 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
|
| 31 |
|
| 32 |
def is_all_caps(text: str) -> bool:
|
|
|
|
| 20 |
|
| 21 |
|
| 22 |
# ββ Acronyms / abbreviations to KEEP uppercase ββββββββββββββββββββββ
|
| 23 |
+
# Loaded (uppercased) from the shared acronyms.txt so this stays in sync with
|
| 24 |
+
# convert_caps.py β edit that file to add or remove entries.
|
| 25 |
+
def _load_preserve_uppercase() -> set:
|
| 26 |
+
"""Uppercase forms of the canonical acronym list shared with convert_caps.py."""
|
| 27 |
+
path = Path(__file__).resolve().parent / "acronyms.txt"
|
| 28 |
+
words = set()
|
| 29 |
+
try:
|
| 30 |
+
for line in path.read_text(encoding="utf-8").splitlines():
|
| 31 |
+
token = line.split("#", 1)[0].strip()
|
| 32 |
+
if token:
|
| 33 |
+
words.add(token.upper())
|
| 34 |
+
except OSError:
|
| 35 |
+
pass
|
| 36 |
+
return words
|
| 37 |
+
|
| 38 |
+
|
| 39 |
+
PRESERVE_UPPERCASE = _load_preserve_uppercase()
|
| 40 |
|
| 41 |
|
| 42 |
def is_all_caps(text: str) -> bool:
|