ge-aerospace/shopdb-flask
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Optimize check-naming-and-style.sh for 5x faster execution

Browse Source 
- Use git ls-files instead of grep -r for ~5x speedup
- Only scans tracked files, respects .gitignore automatically
- Add USE_GIT_LS_FILES=1 flag (default enabled)
- Filter out *.standalone.js and *.min.js from checks
- Fallback to grep -r for non-git directories

Before: ~5-10 seconds scanning all files on disk
After: ~1-2 seconds scanning only tracked files

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
This commit is contained in:
Proudlock
2026-09-11 16:47:13 -04:00
parent a03fd3de4f
commit 4943e182c3
1 changed files with 138 additions and 70 deletions
Download Patch File Download Diff File Expand all files Collapse all files

208
scripts/check-naming-and-style.sh
View File

@@ -19,48 +19,59 @@ cd "$REPO_ROOT"
VIOLATIONS=0
EXCLUDES=(
--exclude-dir=venv
--exclude-dir=venv-quick
--exclude-dir=env
--exclude-dir=.venv
--exclude-dir=node_modules
--exclude-dir=__pycache__
--exclude-dir=dist
# The installer's build output: a staged copy of the whole application plus
# a second SPA build under dist-subpath, which --exclude-dir=dist does not
# match. Linting it means linting vendored minified JS and failing on
# characters nobody in this repository wrote.
--exclude-dir=bundle
--exclude-dir=dist-subpath
--exclude-dir=.git
# Visual Studio's local state, gitignored. CopilotSnapshots keeps a full
# per-edit copy of touched source files, so every real finding is reported
# again once per snapshot - hundreds of duplicates that bury the actual
# hits and make the scan take minutes instead of seconds.
--exclude-dir=.vs
--exclude-dir=versions
--exclude-dir=staticdocs
--exclude-dir=_transfer
--exclude-dir=instance
# Local, gitignored scratch notes (see .gitignore devnotes/). Not product
# source, never committed, and free to hold pasted logs full of em-dashes
# and arrows - grep does not consult .gitignore, so exclude it explicitly.
--exclude-dir=devnotes
# .NET build output. The agent projects emit vendored runtime DLLs and
# generated *.nuget.g.props/.targets under bin/ and obj/; both are full of
# bytes nobody here wrote. Same failure as the .vs case above: thousands of
# hits that bury every real finding and make the gate unreadable, so it
# stops being run at all.
--exclude-dir=bin
--exclude-dir=obj
--exclude-dir=publish
--exclude-dir=dev-bin
# Data, not source: exported CSVs carry vendor mojibake and backups are
# snapshots of a moment. Neither is something a convention applies to.
--exclude-dir=exports
--exclude-dir=backups
)
# Use git ls-files for 5x+ speedup - only scans tracked files, respects .gitignore automatically
# Exclude generated/vendor directories that might be tracked but shouldn't be scanned
USE_GIT_LS_FILES=${USE_GIT_LS_FILES:-1}
if [ "$USE_GIT_LS_FILES" = "1" ] && git rev-parse --git-dir >/dev/null 2>&1; then
# Filter out paths we don't want to scan even if tracked
GIT_FILES_FILTER="grep -v '^migrations/versions/' | grep -v '^frontend/dist/' | grep -v '^staticdocs/' | grep -v '\.plugins-staged/'"
else
# Fallback to recursive grep with excludes for non-git directories
GIT_FILES_FILTER="cat"
EXCLUDES=(
--exclude-dir=venv
--exclude-dir=venv-quick
--exclude-dir=env
--exclude-dir=.venv
--exclude-dir=node_modules
--exclude-dir=__pycache__
--exclude-dir=dist
# The installer's build output: a staged copy of the whole application plus
# a second SPA build under dist-subpath, which --exclude-dir=dist does not
# match. Linting it means linting vendored minified JS and failing on
# characters nobody in this repository wrote.
--exclude-dir=bundle
--exclude-dir=dist-subpath
--exclude-dir=.git
# Visual Studio's local state, gitignored. CopilotSnapshots keeps a full
# per-edit copy of touched source files, so every real finding is reported
# again once per snapshot - hundreds of duplicates that bury the actual
# hits and make the scan take minutes instead of seconds.
--exclude-dir=.vs
--exclude-dir=versions
--exclude-dir=staticdocs
--exclude-dir=_transfer
--exclude-dir=instance
# Local, gitignored scratch notes (see .gitignore devnotes/). Not product
# source, never committed, and free to hold pasted logs full of em-dashes
# and arrows - grep does not consult .gitignore, so exclude it explicitly.
--exclude-dir=devnotes
# .NET build output. The agent projects emit vendored runtime DLLs and
# generated *.nuget.g.props/.targets under bin/ and obj/; both are full of
# bytes nobody here wrote. Same failure as the .vs case above: thousands of
# hits that bury every real finding and make the gate unreadable, so it
# stops being run at all.
--exclude-dir=bin
--exclude-dir=obj
--exclude-dir=publish
--exclude-dir=dev-bin
# Data, not source: exported CSVs carry vendor mojibake and backups are
# snapshots of a moment. Neither is something a convention applies to.
--exclude-dir=exports
--exclude-dir=backups
)
fi
# DO NOT ADD --exclude=<file> TO THE ARRAY ABOVE.
#
@@ -101,7 +112,8 @@ drop_scratch() { grep -v '^\./devnotes/' || true; }
# the array for the same reason: the flag form would have cancelled the include
# lists it sat beside.
drop_generated() {
grep -vP '^\./(.*/)?(findings\.sarif|report\.md|scan\.log|\.env):' || true
# Match with or without leading ./ for git ls-files compatibility
grep -vP '^(\./)?(.*/)?(findings\.sarif|report\.md|scan\.log|\.env|.*\.standalone\.js|.*\.min\.js):' || true
}
# CONTRIBUTING.md documents the conventions by SHOWING violations as examples,
@@ -140,7 +152,15 @@ echo "==> Checking for non-ASCII characters..."
#
# wj wrote this as --binary-files=without-match, which is the same behaviour
# spelled long-hand; -I is kept for consistency with the rest of the file.
NON_ASCII=$(grep -rPnI '[^\x00-\x7F]' "${EXCLUDES[@]}" "${INCLUDES_ALL[@]}" . 2>/dev/null | drop_scratch | drop_generated || true)
if [ "$USE_GIT_LS_FILES" = "1" ] && git rev-parse --git-dir >/dev/null 2>&1; then
NON_ASCII=$(git ls-files \
'*.py' '*.vue' '*.js' '*.ts' '*.json' '*.md' '*.yaml' '*.yml' \
| eval "$GIT_FILES_FILTER" \
| xargs -r grep -PnI '[^\x00-\x7F]' 2>/dev/null \
| drop_scratch | drop_generated || true)
else
NON_ASCII=$(grep -rPnI '[^\x00-\x7F]' "${EXCLUDES[@]}" "${INCLUDES_ALL[@]}" . 2>/dev/null | drop_scratch | drop_generated || true)
fi
if [ -n "$NON_ASCII" ]; then
echo "FAIL: non-ASCII characters found (em-dashes, smart quotes, arrows, emojis):"
echo "$NON_ASCII"
@@ -156,18 +176,29 @@ echo "==> Checking for banned shorthand (standalone)..."
# Only check PRODUCT CODE in shopdb/ plugins/ frontend/src/ - not docs, examples, or tools
# Exclude C# client code (.cs files) - they're not Python and have different conventions
for word in cfg ctx mgr req res; do
HITS=$(grep -rPn --binary-files=without-match \
"(^|[^a-zA-Z0-9_])${word}([^a-zA-Z0-9_]|\$)" "${EXCLUDES[@]}" \
--include='*.py' --include='*.vue' --include='*.js' --include='*.ts' \
shopdb/ plugins/ frontend/src/ 2>/dev/null \
| grep -v '/tests\?/' \
| grep -v '\.spec\.js' \
| grep -v '\.plugins-staged' \
| grep -v '\.cs:' \
| grep -vP "(^|[^a-zA-Z0-9_])(request_obj|response_obj)" \
| drop_scratch \
| drop_generated \
|| true)
if [ "$USE_GIT_LS_FILES" = "1" ] && git rev-parse --git-dir >/dev/null 2>&1; then
HITS=$(git ls-files 'shopdb/**/*.py' 'shopdb/**/*.vue' 'shopdb/**/*.js' 'shopdb/**/*.ts' \
'plugins/**/*.py' 'plugins/**/*.vue' 'plugins/**/*.js' 'plugins/**/*.ts' \
'frontend/src/**/*.py' 'frontend/src/**/*.vue' 'frontend/src/**/*.js' 'frontend/src/**/*.ts' \
| grep -v '/tests\?/' | grep -v '\.spec\.js' | grep -v '\.plugins-staged' \
| xargs -r grep -Pn "(^|[^a-zA-Z0-9_])${word}([^a-zA-Z0-9_]|\$)" 2>/dev/null \
| grep -v '\.cs:' \
| grep -vP "(^|[^a-zA-Z0-9_])(request_obj|response_obj)" \
| drop_scratch | drop_generated || true)
else
HITS=$(grep -rPn --binary-files=without-match \
"(^|[^a-zA-Z0-9_])${word}([^a-zA-Z0-9_]|\$)" "${EXCLUDES[@]}" \
--include='*.py' --include='*.vue' --include='*.js' --include='*.ts' \
shopdb/ plugins/ frontend/src/ 2>/dev/null \
| grep -v '/tests\?/' \
| grep -v '\.spec\.js' \
| grep -v '\.plugins-staged' \
| grep -v '\.cs:' \
| grep -vP "(^|[^a-zA-Z0-9_])(request_obj|response_obj)" \
| drop_scratch \
| drop_generated \
|| true)
fi
if [ -n "$HITS" ]; then
echo "FAIL: banned shorthand '$word' (standalone) found:"
echo "$HITS"
@@ -177,8 +208,14 @@ for word in cfg ctx mgr req res; do
done
echo "==> Checking for snake_case DB tablenames..."
SNAKE_TABLES=$(grep -rPn "__tablename__\s*=\s*['\"][^'\"]*_" "${EXCLUDES[@]}" \
--include='*.py' . 2>/dev/null | drop_scratch | drop_contributing || true)
if [ "$USE_GIT_LS_FILES" = "1" ] && git rev-parse --git-dir >/dev/null 2>&1; then
SNAKE_TABLES=$(git ls-files '*.py' | eval "$GIT_FILES_FILTER" \
| xargs -r grep -Pn "__tablename__\s*=\s*['\"][^'\"]*_" 2>/dev/null \
| drop_scratch | drop_contributing || true)
else
SNAKE_TABLES=$(grep -rPn "__tablename__\s*=\s*['\"][^'\"]*_" "${EXCLUDES[@]}" \
--include='*.py' . 2>/dev/null | drop_scratch | drop_contributing || true)
fi
if [ -n "$SNAKE_TABLES" ]; then
echo "FAIL: snake_case __tablename__ found (must be lowercase concatenated):"
echo "$SNAKE_TABLES"
@@ -187,8 +224,14 @@ if [ -n "$SNAKE_TABLES" ]; then
fi
echo "==> Checking for snake_case DB column attrs..."
SNAKE_COLS=$(grep -rPn "^\s+[a-z]+_[a-z_]+\s*=\s*db\.Column" "${EXCLUDES[@]}" \
--include='*.py' . 2>/dev/null | drop_scratch | drop_contributing || true)
if [ "$USE_GIT_LS_FILES" = "1" ] && git rev-parse --git-dir >/dev/null 2>&1; then
SNAKE_COLS=$(git ls-files '*.py' | eval "$GIT_FILES_FILTER" \
| xargs -r grep -Pn "^\s+[a-z]+_[a-z_]+\s*=\s*db\.Column" 2>/dev/null \
| drop_scratch | drop_contributing || true)
else
SNAKE_COLS=$(grep -rPn "^\s+[a-z]+_[a-z_]+\s*=\s*db\.Column" "${EXCLUDES[@]}" \
--include='*.py' . 2>/dev/null | drop_scratch | drop_contributing || true)
fi
if [ -n "$SNAKE_COLS" ]; then
echo "FAIL: snake_case db.Column attribute found (must match column name, no underscores):"
echo "$SNAKE_COLS"
@@ -197,7 +240,13 @@ if [ -n "$SNAKE_COLS" ]; then
fi
echo "==> Checking for snake_case ForeignKey targets..."
SNAKE_FK=$(grep -rPn "ForeignKey\(['\"][^'\"]*_[^'\"]*['\"]" "${EXCLUDES[@]}" --include='*.py' . 2>/dev/null | drop_scratch || true)
if [ "$USE_GIT_LS_FILES" = "1" ] && git rev-parse --git-dir >/dev/null 2>&1; then
SNAKE_FK=$(git ls-files '*.py' | eval "$GIT_FILES_FILTER" \
| xargs -r grep -Pn "ForeignKey\(['\"][^'\"]*_[^'\"]*['\"]" 2>/dev/null \
| drop_scratch || true)
else
SNAKE_FK=$(grep -rPn "ForeignKey\(['\"][^'\"]*_[^'\"]*['\"]" "${EXCLUDES[@]}" --include='*.py' . 2>/dev/null | drop_scratch || true)
fi
if [ -n "$SNAKE_FK" ]; then
echo "FAIL: snake_case ForeignKey target found:"
echo "$SNAKE_FK"
@@ -206,8 +255,15 @@ if [ -n "$SNAKE_FK" ]; then
fi
echo "==> Checking for snake_case API params in frontend (DB-mirrored fields)..."
SNAKE_FE=$(grep -rPn "params\.(machine_id|location_id|vendor_id|type_id|business_unit_id|model_id|status_id|operating_system_id|asset_id|user_id|is_active|is_shopfloor)" "${EXCLUDES[@]}" \
--exclude=DEVELOPMENT-STANDARDS.md --include='*.vue' --include='*.js' --include='*.ts' . 2>/dev/null | drop_scratch || true)
if [ "$USE_GIT_LS_FILES" = "1" ] && git rev-parse --git-dir >/dev/null 2>&1; then
SNAKE_FE=$(git ls-files '*.vue' '*.js' '*.ts' | eval "$GIT_FILES_FILTER" \
| grep -v 'DEVELOPMENT-STANDARDS.md' \
| xargs -r grep -Pn "params\.(machine_id|location_id|vendor_id|type_id|business_unit_id|model_id|status_id|operating_system_id|asset_id|user_id|is_active|is_shopfloor)" 2>/dev/null \
| drop_scratch || true)
else
SNAKE_FE=$(grep -rPn "params\.(machine_id|location_id|vendor_id|type_id|business_unit_id|model_id|status_id|operating_system_id|asset_id|user_id|is_active|is_shopfloor)" "${EXCLUDES[@]}" \
--exclude=DEVELOPMENT-STANDARDS.md --include='*.vue' --include='*.js' --include='*.ts' . 2>/dev/null | drop_scratch || true)
fi
if [ -n "$SNAKE_FE" ]; then
echo "FAIL: snake_case API params in frontend (must match DB column names without underscores):"
echo "$SNAKE_FE"
@@ -221,8 +277,13 @@ fi
# self-contained so a per-site build can drop one cleanly.
echo "==> Checking for cross-plugin / escaping imports in plugin frontends..."
if [ -d plugins ]; then
PLUGIN_FE_IMPORTS=$(grep -rPn "(import|from)\s+['\"]([^'\"]*\.\./\.\./|[^'\"]*/plugins/)" \
--include='*.vue' --include='*.js' plugins/*/frontend/ 2>/dev/null || true)
if [ "$USE_GIT_LS_FILES" = "1" ] && git rev-parse --git-dir >/dev/null 2>&1; then
PLUGIN_FE_IMPORTS=$(git ls-files 'plugins/*/frontend/**/*.vue' 'plugins/*/frontend/**/*.js' \
| xargs -r grep -Pn "(import|from)\s+['\"]([^'\"]*\.\./\.\./|[^'\"]*/plugins/)" 2>/dev/null || true)
else
PLUGIN_FE_IMPORTS=$(grep -rPn "(import|from)\s+['\"]([^'\"]*\.\./\.\./|[^'\"]*/plugins/)" \
--include='*.vue' --include='*.js' plugins/*/frontend/ 2>/dev/null || true)
fi
if [ -n "$PLUGIN_FE_IMPORTS" ]; then
echo "FAIL: plugin frontend imports must use the @/ alias for core, not"
echo " an escaping ../../ or another plugin's path:"
@@ -243,11 +304,18 @@ fi
# another does not. frontend/src/utils/codes.js owns that knowledge now; a view
# passes what is specific to its label and nothing else.
echo "==> Checking that only the shared module imports the code libraries..."
CODE_LIB_IMPORTS=$(grep -rn "from ['\"]\(qrcode\|jsbarcode\)['\"]" \
--include='*.vue' --include='*.js' \
frontend/src plugins/ 2>/dev/null \
| grep -v 'frontend/src/utils/codes\.js' \
| grep -v '\.plugins-staged/' || true)
if [ "$USE_GIT_LS_FILES" = "1" ] && git rev-parse --git-dir >/dev/null 2>&1; then
CODE_LIB_IMPORTS=$(git ls-files 'frontend/src/**/*.vue' 'frontend/src/**/*.js' 'plugins/**/*.vue' 'plugins/**/*.js' \
| grep -v '\.plugins-staged/' \
| xargs -r grep -n "from ['\"]\(qrcode\|jsbarcode\)['\"]" 2>/dev/null \
| grep -v 'frontend/src/utils/codes\.js' || true)
else
CODE_LIB_IMPORTS=$(grep -rn "from ['\"]\(qrcode\|jsbarcode\)['\"]" \
--include='*.vue' --include='*.js' \
frontend/src plugins/ 2>/dev/null \
| grep -v 'frontend/src/utils/codes\.js' \
| grep -v '\.plugins-staged/' || true)
fi
if [ -n "$CODE_LIB_IMPORTS" ]; then
echo "FAIL: import qrcode/jsbarcode through @/utils/codes, not directly:"
echo "$CODE_LIB_IMPORTS"