Files
spec-kit/scripts/bash/common.sh
Pierluigi Lenoci 2e55bdd3f2 fix(scripts): encode residual JSON control chars as \uXXXX instead of stripping (#1872)
* fix(scripts): encode residual control chars as \uXXXX instead of stripping

json_escape() was silently deleting control characters (U+0000-U+001F)
that were not individually handled (\n, \t, \r, \b, \f). Per RFC 8259,
these must be encoded as \uXXXX sequences to preserve data integrity.

Replace the tr -d strip with a char-by-char loop that emits proper
\uXXXX escapes for any remaining control characters.

* fix(scripts): address Copilot review on json_escape control char loop

- Set LC_ALL=C for the entire loop (not just printf) so that ${#s} and
  ${s:$i:1} operate on bytes deterministically across locales
- Fix comment: U+0000 (NUL) cannot exist in bash strings, range is
  U+0001-U+001F; adjust code guard accordingly (code >= 1)
- Emit directly to stdout instead of accumulating in a variable,
  avoiding quadratic string concatenation on longer inputs

* perf(scripts): use printf -v to avoid subshell in json_escape loop

Replace code=$(printf ...) with printf -v code to assign the character
code without spawning a subshell on every byte, reducing overhead for
longer inputs.
2026-03-18 07:58:34 -05:00

276 lines
9.7 KiB
Bash

#!/usr/bin/env bash
# Common functions and variables for all scripts
# Get repository root, with fallback for non-git repositories
get_repo_root() {
if git rev-parse --show-toplevel >/dev/null 2>&1; then
git rev-parse --show-toplevel
else
# Fall back to script location for non-git repos
local script_dir="$(CDPATH="" cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
(cd "$script_dir/../../.." && pwd)
fi
}
# Get current branch, with fallback for non-git repositories
get_current_branch() {
# First check if SPECIFY_FEATURE environment variable is set
if [[ -n "${SPECIFY_FEATURE:-}" ]]; then
echo "$SPECIFY_FEATURE"
return
fi
# Then check git if available
if git rev-parse --abbrev-ref HEAD >/dev/null 2>&1; then
git rev-parse --abbrev-ref HEAD
return
fi
# For non-git repos, try to find the latest feature directory
local repo_root=$(get_repo_root)
local specs_dir="$repo_root/specs"
if [[ -d "$specs_dir" ]]; then
local latest_feature=""
local highest=0
for dir in "$specs_dir"/*; do
if [[ -d "$dir" ]]; then
local dirname=$(basename "$dir")
if [[ "$dirname" =~ ^([0-9]{3})- ]]; then
local number=${BASH_REMATCH[1]}
number=$((10#$number))
if [[ "$number" -gt "$highest" ]]; then
highest=$number
latest_feature=$dirname
fi
fi
fi
done
if [[ -n "$latest_feature" ]]; then
echo "$latest_feature"
return
fi
fi
echo "main" # Final fallback
}
# Check if we have git available
has_git() {
git rev-parse --show-toplevel >/dev/null 2>&1
}
check_feature_branch() {
local branch="$1"
local has_git_repo="$2"
# For non-git repos, we can't enforce branch naming but still provide output
if [[ "$has_git_repo" != "true" ]]; then
echo "[specify] Warning: Git repository not detected; skipped branch validation" >&2
return 0
fi
if [[ ! "$branch" =~ ^[0-9]{3}- ]]; then
echo "ERROR: Not on a feature branch. Current branch: $branch" >&2
echo "Feature branches should be named like: 001-feature-name" >&2
return 1
fi
return 0
}
get_feature_dir() { echo "$1/specs/$2"; }
# Find feature directory by numeric prefix instead of exact branch match
# This allows multiple branches to work on the same spec (e.g., 004-fix-bug, 004-add-feature)
find_feature_dir_by_prefix() {
local repo_root="$1"
local branch_name="$2"
local specs_dir="$repo_root/specs"
# Extract numeric prefix from branch (e.g., "004" from "004-whatever")
if [[ ! "$branch_name" =~ ^([0-9]{3})- ]]; then
# If branch doesn't have numeric prefix, fall back to exact match
echo "$specs_dir/$branch_name"
return
fi
local prefix="${BASH_REMATCH[1]}"
# Search for directories in specs/ that start with this prefix
local matches=()
if [[ -d "$specs_dir" ]]; then
for dir in "$specs_dir"/"$prefix"-*; do
if [[ -d "$dir" ]]; then
matches+=("$(basename "$dir")")
fi
done
fi
# Handle results
if [[ ${#matches[@]} -eq 0 ]]; then
# No match found - return the branch name path (will fail later with clear error)
echo "$specs_dir/$branch_name"
elif [[ ${#matches[@]} -eq 1 ]]; then
# Exactly one match - perfect!
echo "$specs_dir/${matches[0]}"
else
# Multiple matches - this shouldn't happen with proper naming convention
echo "ERROR: Multiple spec directories found with prefix '$prefix': ${matches[*]}" >&2
echo "Please ensure only one spec directory exists per numeric prefix." >&2
return 1
fi
}
get_feature_paths() {
local repo_root=$(get_repo_root)
local current_branch=$(get_current_branch)
local has_git_repo="false"
if has_git; then
has_git_repo="true"
fi
# Use prefix-based lookup to support multiple branches per spec
local feature_dir
if ! feature_dir=$(find_feature_dir_by_prefix "$repo_root" "$current_branch"); then
echo "ERROR: Failed to resolve feature directory" >&2
return 1
fi
# Use printf '%q' to safely quote values, preventing shell injection
# via crafted branch names or paths containing special characters
printf 'REPO_ROOT=%q\n' "$repo_root"
printf 'CURRENT_BRANCH=%q\n' "$current_branch"
printf 'HAS_GIT=%q\n' "$has_git_repo"
printf 'FEATURE_DIR=%q\n' "$feature_dir"
printf 'FEATURE_SPEC=%q\n' "$feature_dir/spec.md"
printf 'IMPL_PLAN=%q\n' "$feature_dir/plan.md"
printf 'TASKS=%q\n' "$feature_dir/tasks.md"
printf 'RESEARCH=%q\n' "$feature_dir/research.md"
printf 'DATA_MODEL=%q\n' "$feature_dir/data-model.md"
printf 'QUICKSTART=%q\n' "$feature_dir/quickstart.md"
printf 'CONTRACTS_DIR=%q\n' "$feature_dir/contracts"
}
# Check if jq is available for safe JSON construction
has_jq() {
command -v jq >/dev/null 2>&1
}
# Escape a string for safe embedding in a JSON value (fallback when jq is unavailable).
# Handles backslash, double-quote, and JSON-required control character escapes (RFC 8259).
json_escape() {
local s="$1"
s="${s//\\/\\\\}"
s="${s//\"/\\\"}"
s="${s//$'\n'/\\n}"
s="${s//$'\t'/\\t}"
s="${s//$'\r'/\\r}"
s="${s//$'\b'/\\b}"
s="${s//$'\f'/\\f}"
# Escape any remaining U+0001-U+001F control characters as \uXXXX.
# (U+0000/NUL cannot appear in bash strings and is excluded.)
# LC_ALL=C ensures ${#s} counts bytes and ${s:$i:1} yields single bytes,
# so multi-byte UTF-8 sequences (first byte >= 0xC0) pass through intact.
local LC_ALL=C
local i char code
for (( i=0; i<${#s}; i++ )); do
char="${s:$i:1}"
printf -v code '%d' "'$char" 2>/dev/null || code=256
if (( code >= 1 && code <= 31 )); then
printf '\\u%04x' "$code"
else
printf '%s' "$char"
fi
done
}
check_file() { [[ -f "$1" ]] && echo "$2" || echo "$2"; }
check_dir() { [[ -d "$1" && -n $(ls -A "$1" 2>/dev/null) ]] && echo "$2" || echo "$2"; }
# Resolve a template name to a file path using the priority stack:
# 1. .specify/templates/overrides/
# 2. .specify/presets/<preset-id>/templates/ (sorted by priority from .registry)
# 3. .specify/extensions/<ext-id>/templates/
# 4. .specify/templates/ (core)
resolve_template() {
local template_name="$1"
local repo_root="$2"
local base="$repo_root/.specify/templates"
# Priority 1: Project overrides
local override="$base/overrides/${template_name}.md"
[ -f "$override" ] && echo "$override" && return 0
# Priority 2: Installed presets (sorted by priority from .registry)
local presets_dir="$repo_root/.specify/presets"
if [ -d "$presets_dir" ]; then
local registry_file="$presets_dir/.registry"
if [ -f "$registry_file" ] && command -v python3 >/dev/null 2>&1; then
# Read preset IDs sorted by priority (lower number = higher precedence).
# The python3 call is wrapped in an if-condition so that set -e does not
# abort the function when python3 exits non-zero (e.g. invalid JSON).
local sorted_presets=""
if sorted_presets=$(SPECKIT_REGISTRY="$registry_file" python3 -c "
import json, sys, os
try:
with open(os.environ['SPECKIT_REGISTRY']) as f:
data = json.load(f)
presets = data.get('presets', {})
for pid, meta in sorted(presets.items(), key=lambda x: x[1].get('priority', 10)):
print(pid)
except Exception:
sys.exit(1)
" 2>/dev/null); then
if [ -n "$sorted_presets" ]; then
# python3 succeeded and returned preset IDs — search in priority order
while IFS= read -r preset_id; do
local candidate="$presets_dir/$preset_id/templates/${template_name}.md"
[ -f "$candidate" ] && echo "$candidate" && return 0
done <<< "$sorted_presets"
fi
# python3 succeeded but registry has no presets — nothing to search
else
# python3 failed (missing, or registry parse error) — fall back to unordered directory scan
for preset in "$presets_dir"/*/; do
[ -d "$preset" ] || continue
local candidate="$preset/templates/${template_name}.md"
[ -f "$candidate" ] && echo "$candidate" && return 0
done
fi
else
# Fallback: alphabetical directory order (no python3 available)
for preset in "$presets_dir"/*/; do
[ -d "$preset" ] || continue
local candidate="$preset/templates/${template_name}.md"
[ -f "$candidate" ] && echo "$candidate" && return 0
done
fi
fi
# Priority 3: Extension-provided templates
local ext_dir="$repo_root/.specify/extensions"
if [ -d "$ext_dir" ]; then
for ext in "$ext_dir"/*/; do
[ -d "$ext" ] || continue
# Skip hidden directories (e.g. .backup, .cache)
case "$(basename "$ext")" in .*) continue;; esac
local candidate="$ext/templates/${template_name}.md"
[ -f "$candidate" ] && echo "$candidate" && return 0
done
fi
# Priority 4: Core templates
local core="$base/${template_name}.md"
[ -f "$core" ] && echo "$core" && return 0
# Template not found in any location.
# Return 1 so callers can distinguish "not found" from "found".
# Callers running under set -e should use: TEMPLATE=$(resolve_template ...) || true
return 1
}