Files
stack/packages/mosaic/framework/tools/git/detect-platform.sh
Hermes Agent 6053e1ee4c
All checks were successful
ci/woodpecker/pr/ci Pipeline was successful
fix(git): fail closed on tabs the YAML fallback recognizer would swallow (#865)
PyYAML raises a ScannerError on a tab used anywhere outside a quoted
scalar (leading/trailing/embedded in a plain value, immediately before or
after a key colon, or as indentation) and yields no token, accepting tabs
ONLY inside single/double-quoted scalars. The conservative block-YAML
fallback in get_gitea_token_for_login normalized those tabs away -- via
_scalar's top-level .strip(), _KEY_RE's [ \t] separators, _Parser.__init__'s
body.rstrip(), parse_seq's body[1:].strip(), and the inline-map emptiness
checks -- and still emitted the login token: a credential fail-open in the
dangerous direction (less conservative than PyYAML).

Extend the whole-document "only ever more conservative than PyYAML, never
less" invariant to tab/scanner parity:
- _KEY_RE now uses SPACE-only separators (` *:` / `[ ](.*)`), so a tab in a
  key/value separator makes the line fail to match and the caller fails closed.
- Every whitespace-normalization site strips SPACES only (strip(" ")/rstrip(" "))
  so a tab survives to a fail-closed guard instead of being silently removed:
  _scalar top-level strip, quoted-trailing strip, post-comment strip,
  _Parser.__init__ body rstrip, parse_seq item strip, and the three inline
  emptiness checks.
- _scalar fails closed on any tab remaining in a plain scalar.
Tabs strictly inside quoted scalars are preserved verbatim (unchanged parity),
matching exactly what PyYAML accepts.

Verified empirically against PyYAML 6.0.3: ScannerError for each rejected
tab position; string-preserved for quoted inner tabs. Differential fuzz with
tab re-included: 0 fail-opens over ~6000 inputs; 0 over-rejection across 220
PyYAML-accepted quoted-tab cases. Adds section 17 to the regression harness
(fail-close fixtures for trailing/leading/embedded/after-colon/indentation
tabs; parity fixtures for double- and single-quoted inner tabs).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-22 00:05:39 -05:00

1218 lines
44 KiB
Bash
Executable File

#!/bin/bash
# detect-platform.sh - Detect git platform (Gitea or GitHub) for current repo
# Usage: source detect-platform.sh && detect_platform
# or: ./detect-platform.sh (prints platform name)
detect_platform() {
local remote_url
remote_url=$(git remote get-url origin 2>/dev/null)
if [[ -z "$remote_url" ]]; then
echo "error: not a git repository or no origin remote" >&2
return 1
fi
# Check for GitHub
if [[ "$remote_url" == *"github.com"* ]]; then
PLATFORM="github"
export PLATFORM
echo "github"
return 0
fi
# Check for common Gitea indicators
# Gitea URLs typically don't contain github.com, gitlab.com, bitbucket.org
if [[ "$remote_url" != *"gitlab.com"* ]] && \
[[ "$remote_url" != *"bitbucket.org"* ]]; then
# Assume Gitea for self-hosted repos
PLATFORM="gitea"
export PLATFORM
echo "gitea"
return 0
fi
PLATFORM="unknown"
export PLATFORM
echo "unknown"
return 1
}
get_repo_info() {
local remote_url
remote_url=$(git remote get-url origin 2>/dev/null)
if [[ -z "$remote_url" ]]; then
echo "error: not a git repository or no origin remote" >&2
return 1
fi
# Extract owner/repo from URL
# Handles: git@host:owner/repo.git, https://host/owner/repo.git, https://host/owner/repo
local repo_path
if [[ "$remote_url" == git@* ]]; then
repo_path="${remote_url#*:}"
else
repo_path="${remote_url#*://}"
repo_path="${repo_path#*/}"
fi
# Remove .git suffix if present
repo_path="${repo_path%.git}"
echo "$repo_path"
}
get_repo_owner() {
local repo_info
repo_info=$(get_repo_info)
echo "${repo_info%%/*}"
}
get_repo_name() {
local repo_info
repo_info=$(get_repo_info)
echo "${repo_info##*/}"
}
get_repo_slug() {
get_repo_info
}
gitea_url_matches_host() {
local url="${1:-}" host="${2:-}"
[[ -n "$url" && -n "$host" ]] || return 1
python3 - "$url" "$host" <<'PY'
import sys
from urllib.parse import urlparse
url, remote_host = sys.argv[1:]
configured = urlparse(url)
remote = urlparse(f"//{remote_host}")
if configured.scheme not in {"http", "https"} or configured.hostname != remote.hostname:
raise SystemExit(1)
# Normalize by scheme: an implicit (portless) HTTP(S) URL and its explicit
# default-port form (":80" for http, ":443" for https) name the same
# provider endpoint. Apply that equivalence symmetrically -- whichever side
# omits the port is treated as carrying the scheme's default port -- so
# "configured implicit vs. remote explicit" and "configured explicit vs.
# remote implicit" both match. (The remote side here is always an HTTP(S)
# authority; an SSH remote's transport port is stripped by get_remote_host
# before reaching this comparison, since it identifies an unrelated
# service on the same host, not the HTTP(S) provider port.)
default_port = 80 if configured.scheme == "http" else 443
normalized_configured = configured.port if configured.port is not None else default_port
normalized_remote = remote.port if remote.port is not None else default_port
if normalized_configured != normalized_remote:
raise SystemExit(1)
raise SystemExit(0)
PY
}
get_gitea_service_for_host() {
local host="$1"
local cred_file="${MOSAIC_CREDENTIALS_FILE:-}"
if [[ -z "$cred_file" ]]; then
# Same resolution chain as _lib/credentials.sh: profile HOME, then
# host-level /etc only if it exists; neither existing keeps the
# $HOME default (matches the lib's final := fallback).
cred_file="$HOME/.config/mosaic/credentials.json"
if [[ ! -f "$cred_file" && -f /etc/mosaic/credentials.json ]]; then
cred_file="/etc/mosaic/credentials.json"
fi
fi
case "$host" in
git.mosaicstack.dev)
echo "mosaicstack"
return 0
;;
git.uscllc.com)
echo "usc"
return 0
;;
esac
[[ -f "$cred_file" ]] || return 1
command -v jq >/dev/null 2>&1 || return 1
jq -r --arg host "$host" '
.gitea // {}
| to_entries[]
| select((.value.url // "" | sub("/+$"; "")) | test("https?://" + $host + "$"))
| .key
' "$cred_file" | head -n 1
}
find_tea_login_for_host() {
local host="$1"
local logins_json
command -v tea >/dev/null 2>&1 || return 1
logins_json=$(tea login list --output json 2>/dev/null) || return 1
TEA_LOGINS_JSON="$logins_json" python3 - "$host" <<'PY'
import json
import os
import sys
from urllib.parse import urlparse
host = sys.argv[1]
try:
logins = json.loads(os.environ.get("TEA_LOGINS_JSON", "[]"))
except Exception:
raise SystemExit(1)
for login in logins if isinstance(logins, list) else []:
url = str(login.get("url") or login.get("URL") or "")
name = str(login.get("name") or login.get("Name") or "")
parsed = urlparse(url)
if parsed.hostname == host and name:
print(name)
raise SystemExit(0)
raise SystemExit(1)
PY
}
tea_login_matches_host() {
local login_name="$1" host="$2"
local logins_json
command -v tea >/dev/null 2>&1 || return 1
logins_json=$(tea login list --output json 2>/dev/null) || return 1
TEA_LOGINS_JSON="$logins_json" python3 - "$login_name" "$host" <<'PY'
import json
import os
import sys
from urllib.parse import urlparse
login_name, host = sys.argv[1], sys.argv[2]
try:
logins = json.loads(os.environ.get("TEA_LOGINS_JSON", "[]"))
except Exception:
raise SystemExit(1)
for login in logins if isinstance(logins, list) else []:
url = str(login.get("url") or login.get("URL") or "")
name = str(login.get("name") or login.get("Name") or "")
parsed = urlparse(url)
if name == login_name and parsed.hostname == host:
raise SystemExit(0)
raise SystemExit(1)
PY
}
# Emit an actionable diagnostic to stderr when no tea login resolves for a host.
# Callers that have a working API fallback may ignore the non-zero return of
# get_gitea_login_for_host; this turns the previously SILENT failure into a loud,
# greppable hint (available logins + override + add-login instructions). Printed to
# stderr only, so it never contaminates stdout (the resolved login name) or log
# assertions that capture tea/curl invocations.
print_gitea_login_diagnostic() {
local host="${1:-<unknown>}"
local available
available=$(
command -v tea >/dev/null 2>&1 || { echo "(tea CLI not installed)"; exit 0; }
logins_json=$(tea login list --output json 2>/dev/null) || { echo "(could not query tea login list)"; exit 0; }
TEA_LOGINS_JSON="$logins_json" python3 - <<'PY'
import json, os
from urllib.parse import urlparse
try:
logins = json.loads(os.environ.get("TEA_LOGINS_JSON", "[]"))
except Exception:
logins = []
rows = []
for login in logins if isinstance(logins, list) else []:
name = str(login.get("name") or login.get("Name") or "")
url = str(login.get("url") or login.get("URL") or "")
host = urlparse(url).hostname or "?"
if name:
rows.append(f"{name} (host: {host})")
print("; ".join(rows) if rows else "(none configured)")
PY
)
{
echo "Error: no Gitea tea login matches host '$host'."
echo " Available tea logins: ${available}"
echo " Fix: set GITEA_LOGIN to a login whose URL host is '$host',"
echo " or add one: tea login add --name <name> --url https://$host --token <token>"
} >&2
}
get_gitea_login_for_host() {
local host="${1:-}"
local login
if [[ -z "$host" ]]; then
host=$(get_remote_host) || return 1
fi
if [[ -n "${GITEA_LOGIN:-}" ]]; then
if tea_login_matches_host "$GITEA_LOGIN" "$host"; then
echo "$GITEA_LOGIN"
return 0
fi
fi
login=$(find_tea_login_for_host "$host" || true)
if [[ -n "$login" ]]; then
echo "$login"
return 0
fi
print_gitea_login_diagnostic "$host"
return 1
}
# Validate the current authenticated Gitea user for a resolved Tea login.
# Tea stores a user name with each login which can become stale after user rename,
# token rotation, or server migration. Querying /user derives the identity from the
# active credential instead of trusting that saved name. Callers fall back to the
# host-scoped API path when this validation fails.
get_gitea_authenticated_user() {
local login_name="$1" response
command -v tea >/dev/null 2>&1 || return 1
response=$(tea api --login "$login_name" /user 2>/dev/null) || return 1
TEA_AUTHENTICATED_USER_JSON="$response" python3 - <<'PY'
import json
import os
try:
user = json.loads(os.environ["TEA_AUTHENTICATED_USER_JSON"])
except (KeyError, json.JSONDecodeError):
raise SystemExit(1)
login = user.get("login") if isinstance(user, dict) else None
if isinstance(login, str) and login:
print(login)
raise SystemExit(0)
raise SystemExit(1)
PY
}
get_default_tea_login() {
local logins_json
command -v tea >/dev/null 2>&1 || return 1
logins_json=$(tea login list --output json 2>/dev/null) || return 1
TEA_LOGINS_JSON="$logins_json" python3 - <<'PY'
import json
import os
try:
logins = json.loads(os.environ.get("TEA_LOGINS_JSON", "[]"))
except Exception:
raise SystemExit(1)
if not isinstance(logins, list) or not logins:
raise SystemExit(1)
for login in logins:
if not isinstance(login, dict):
continue
is_default = str(login.get("default") or login.get("Default") or "").lower()
name = str(login.get("name") or login.get("Name") or "")
if name and is_default == "true":
print(name)
raise SystemExit(0)
for login in logins:
if not isinstance(login, dict):
continue
name = str(login.get("name") or login.get("Name") or "")
if name:
print(name)
raise SystemExit(0)
raise SystemExit(1)
PY
}
get_gitea_login_for_repo_override() {
local login
if [[ -n "${GITEA_LOGIN:-}" ]]; then
echo "$GITEA_LOGIN"
return 0
fi
login=$(get_default_tea_login || true)
if [[ -n "$login" ]]; then
echo "$login"
return 0
fi
return 1
}
get_host_from_url() {
local url="${1:-}"
[[ -n "$url" ]] || return 1
python3 - "$url" <<'PY'
import sys
from urllib.parse import urlparse
parsed = urlparse(sys.argv[1])
if parsed.hostname:
print(parsed.hostname)
raise SystemExit(0)
raise SystemExit(1)
PY
}
get_gitea_api_host_for_repo_override() {
if [[ -n "${GITEA_HOST:-}" ]]; then
echo "$GITEA_HOST"
return 0
fi
get_host_from_url "${GITEA_URL:-}"
}
# Resolve owner/repo relative to a configured Gitea base URL. HTTP(S) clone
# URLs can include the deployment prefix (for example /gitea/owner/repo.git),
# but Gitea's /repos API expects only owner/repo. Root-mounted and SSH clone
# forms retain their existing owner/repo behavior.
get_gitea_repo_slug_for_url() {
local configured_url="$1" remote_url
remote_url=$(git remote get-url origin 2>/dev/null) || return 1
if [[ "$remote_url" =~ ^https?:// ]]; then
python3 - "$remote_url" "$configured_url" <<'PY'
import sys
from urllib.parse import urlparse
remote = urlparse(sys.argv[1])
base = urlparse(sys.argv[2])
remote_path = remote.path.strip("/")
if remote_path.endswith(".git"):
remote_path = remote_path[:-4]
base_path = base.path.strip("/")
remote_parts = [part for part in remote_path.split("/") if part]
base_parts = [part for part in base_path.split("/") if part]
if base_parts and remote_parts[:len(base_parts)] == base_parts:
repo_parts = remote_parts[len(base_parts):]
elif len(remote_parts) == 2:
# Preserve a root-shaped clone URL when provider API configuration carries
# a reverse-proxy prefix separately.
repo_parts = remote_parts
else:
raise SystemExit(1)
if len(repo_parts) != 2:
raise SystemExit(1)
print("/".join(repo_parts))
PY
return
fi
get_repo_slug
}
get_gitea_repo_args() {
local repo host login
repo=$(get_repo_slug) || return 1
host=$(get_remote_host) || return 1
login=$(get_gitea_login_for_host "$host") || return 1
printf -- '--repo %q --login %q' "$repo" "$login"
}
get_gitea_login() {
get_gitea_login_for_host "$(get_remote_host)"
}
get_remote_host() {
local remote_url
remote_url=$(git remote get-url origin 2>/dev/null || true)
if [[ -z "$remote_url" ]]; then
return 1
fi
if [[ "$remote_url" =~ ^https?://([^/]+)/ ]]; then
local host="${BASH_REMATCH[1]}"
echo "${host##*@}"
return 0
fi
if [[ "$remote_url" =~ ^ssh://([^/]+)/ ]]; then
local host="${BASH_REMATCH[1]}"
host="${host##*@}"
# Strip an SSH transport port (e.g. "git.example:2222"): it names the
# SSH daemon port, not the HTTP(S) provider API port, and must not
# feed gitea_url_matches_host's port comparison (#850).
echo "${host%%:*}"
return 0
fi
if [[ "$remote_url" =~ ^git@([^:]+): ]]; then
echo "${BASH_REMATCH[1]}"
return 0
fi
return 1
}
# Resolve the configured Gitea base URL for a host from the same credential
# source used by get_gitea_token. The scheme and any deployment path prefix are
# provider configuration and must not be reconstructed from the git remote.
get_gitea_url_for_host() {
local host="$1" script_dir cred_loader url
script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
cred_loader="$script_dir/../_lib/credentials.sh"
if [[ -f "$cred_loader" ]]; then
url=$(
# shellcheck source=/dev/null
source "$cred_loader"
unset GITEA_TOKEN GITEA_URL
case "$host" in
git.mosaicstack.dev) load_credentials gitea-mosaicstack 2>/dev/null ;;
git.uscllc.com) load_credentials gitea-usc 2>/dev/null ;;
*)
for svc in gitea-mosaicstack gitea-usc; do
unset GITEA_TOKEN GITEA_URL
load_credentials "$svc" 2>/dev/null || continue
if gitea_url_matches_host "${GITEA_URL:-}" "$host"; then
break
fi
unset GITEA_TOKEN GITEA_URL
done
;;
esac
if gitea_url_matches_host "${GITEA_URL:-}" "$host"; then
printf '%s' "${GITEA_URL%/}"
fi
)
if [[ -n "$url" ]]; then
printf '%s\n' "$url"
return 0
fi
fi
if gitea_url_matches_host "${GITEA_URL:-}" "$host"; then
printf '%s\n' "${GITEA_URL%/}"
return 0
fi
return 1
}
# Resolve a Gitea API token for the given host.
# Priority: Mosaic credential loader → GITEA_TOKEN env → ~/.git-credentials
get_gitea_token() {
local host="$1"
local script_dir
script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
local cred_loader="$script_dir/../_lib/credentials.sh"
# 1. Mosaic credential loader (host → service mapping, run in subshell to avoid polluting env)
if [[ -f "$cred_loader" ]]; then
local token
token=$(
# shellcheck source=/dev/null
source "$cred_loader"
# Host-specific wrapper resolution must not inherit caller/global GITEA_*.
# load_credentials intentionally preserves existing env vars for interactive use,
# but metadata/merge wrappers need credentials matching the remote host.
unset GITEA_TOKEN GITEA_URL
case "$host" in
git.mosaicstack.dev) load_credentials gitea-mosaicstack 2>/dev/null ;;
git.uscllc.com) load_credentials gitea-usc 2>/dev/null ;;
*)
local matched=false
for svc in gitea-mosaicstack gitea-usc; do
unset GITEA_TOKEN GITEA_URL
load_credentials "$svc" 2>/dev/null || continue
if gitea_url_matches_host "${GITEA_URL:-}" "$host"; then
matched=true
break
fi
done
if [[ "$matched" != true ]]; then
unset GITEA_TOKEN GITEA_URL
fi
;;
esac
echo "${GITEA_TOKEN:-}"
)
if [[ -n "$token" ]]; then
echo "$token"
return 0
fi
fi
# 2. GITEA_TOKEN env var (only when GITEA_URL, if present, matches the remote host)
if [[ -n "${GITEA_TOKEN:-}" ]]; then
if [[ -z "${GITEA_URL:-}" ]] || gitea_url_matches_host "$GITEA_URL" "$host"; then
echo "$GITEA_TOKEN"
return 0
fi
fi
# 3. ~/.git-credentials file
local creds="$HOME/.git-credentials"
if [[ -f "$creds" ]]; then
local token
token=$(grep -F "$host" "$creds" 2>/dev/null | sed -n 's#https\?://[^@]*:\([^@/]*\)@.*#\1#p' | head -n 1)
if [[ -n "$token" ]]; then
echo "$token"
return 0
fi
fi
return 1
}
# Stage the Gitea bearer credential for curl OUTSIDE the process argument vector.
# Passing "-H 'Authorization: token <value>'" on the curl command line exposes
# the token to anyone who can read the process table (ps / /proc/<pid>/cmdline)
# for the lifetime of the request. Instead, write the header into a private
# (mode 0600) curl config file and have callers pass it with `curl --config`, so
# only the FILE PATH — never the token — appears in argv. Prints the temp file
# path on success; the caller OWNS the file and MUST remove it on every exit
# path (success and failure). $1 = bearer token. Callers must not log the token.
gitea_write_auth_config() {
local token="$1" auth_file
auth_file=$(mktemp "${TMPDIR:-/tmp}/mosaic-gitea-auth.XXXXXX") || return 1
# mktemp already creates the file with 0600; be explicit in case of an
# unusual umask so the credential is never briefly group/other readable.
chmod 600 "$auth_file" 2>/dev/null || true
# `header = "..."` is curl's config syntax for an extra request header. Only
# this filename reaches curl's argv; the token stays on disk, readable solely
# by this user, and is unlinked by the caller's trap after the request.
if ! printf 'header = "Authorization: token %s"\n' "$token" > "$auth_file"; then
rm -f "$auth_file"
return 1
fi
printf '%s' "$auth_file"
}
# Resolve the API token for a SPECIFIC tea login name from tea's own config
# (the same store tea itself writes/reads for `--login <name>`). This is what
# lets a REST write be performed AS the selected --login identity: tea keys its
# per-login tokens by `name` in $XDG_CONFIG_HOME/tea/config.yml (default
# ~/.config/tea/config.yml), exactly as the `tea` CLI resolves them, so a
# --login override and its REST read-back bind to the SAME credential/identity.
#
# $2 (repo host) binds the selected credential to the TARGET host: a tea login
# also records the `url` it authenticates against, and the matched login's URL
# host MUST equal the repo host. This fails closed when an override login is
# configured for a DIFFERENT host than the repo remote, so a login name shared
# across hosts (or a mistargeted override) can never send one host's credential
# to another host (cross-host credential leak). When $2 is empty the host bind
# is skipped (host-agnostic lookup) — callers that write should always pass it.
#
# Prints the token on success; returns non-zero (no output) if the config, a
# matching login token, or the host bind cannot be satisfied. Callers must not
# log the result.
get_gitea_token_for_login() {
local login_name="$1" repo_host="${2:-}" config_file
[[ -n "$login_name" ]] || return 1
config_file="${XDG_CONFIG_HOME:-$HOME/.config}/tea/config.yml"
[[ -f "$config_file" ]] || return 1
LOGIN_NAME="$login_name" REPO_HOST="$repo_host" python3 - "$config_file" <<'PY'
import datetime
import os
import re
import sys
from urllib.parse import urlparse
wanted = os.environ["LOGIN_NAME"]
repo_host = os.environ.get("REPO_HOST", "").strip().lower()
config_path = sys.argv[1]
# PyYAML 6.0.3 SafeLoader implicit resolver patterns (YAML 1.1). An UNQUOTED
# plain scalar matching any of these is resolved by PyYAML to a NON-string type
# (null->None, bool, int, float, timestamp->date/datetime); a quoted scalar is
# ALWAYS a string. These mirror yaml/resolver.py so the PyYAML-absent fallback
# types unquoted scalars exactly as PyYAML would (see _implicit_nonstring).
_IMPLICIT_NULL = re.compile(r"^(?:~|null|Null|NULL|)$")
_IMPLICIT_BOOL = re.compile(
r"^(?:yes|Yes|YES|no|No|NO|true|True|TRUE|false|False|FALSE"
r"|on|On|ON|off|Off|OFF)$"
)
_IMPLICIT_INT = re.compile(
r"^(?:[-+]?0b[0-1_]+"
r"|[-+]?0[0-7_]+"
r"|[-+]?(?:0|[1-9][0-9_]*)"
r"|[-+]?0x[0-9a-fA-F_]+"
r"|[-+]?[1-9][0-9_]*(?::[0-5]?[0-9])+)$"
)
_IMPLICIT_FLOAT = re.compile(
r"^(?:[-+]?(?:[0-9][0-9_]*)\.[0-9_]*(?:[eE][-+]?[0-9]+)?"
r"|\.[0-9][0-9_]*(?:[eE][-+]?[0-9]+)?"
r"|[-+]?[0-9][0-9_]*(?::[0-5]?[0-9])+\.[0-9_]*"
r"|[-+]?\.(?:inf|Inf|INF)"
r"|\.(?:nan|NaN|NAN))$"
)
_IMPLICIT_TIMESTAMP = re.compile(
r"^(?:[0-9][0-9][0-9][0-9]-[0-9][0-9]-[0-9][0-9]"
r"|[0-9][0-9][0-9][0-9]-[0-9][0-9]?-[0-9][0-9]?"
r"(?:[Tt]|[ \t]+)[0-9][0-9]?"
r":[0-9][0-9]:[0-9][0-9](?:\.[0-9]*)?"
r"(?:[ \t]*(?:Z|[-+][0-9][0-9]?(?::[0-9][0-9])?))?)$"
)
def _implicit_nonstring(text):
# True when an UNQUOTED plain scalar would be resolved by PyYAML's SafeLoader
# to a non-string type (null/bool/int/float/timestamp). Fuzzed against real
# PyYAML 6.0.3: it never returns False where PyYAML types the scalar as a
# non-string (i.e. never fail-open), and is at worst MORE conservative on a
# couple of degenerate float spellings (e.g. "4.e8") that PyYAML keeps as a
# string -- the safe direction for this credential-selecting fallback.
return bool(
_IMPLICIT_NULL.match(text)
or _IMPLICIT_BOOL.match(text)
or _IMPLICIT_INT.match(text)
or _IMPLICIT_FLOAT.match(text)
or _IMPLICIT_TIMESTAMP.match(text)
)
# PyYAML 6.0.3 SafeConstructor timestamp regexp (yaml/constructor.py). The
# constructor RE-parses a timestamp-tagged scalar with THIS pattern and then
# builds a datetime.date/datetime, which raises ValueError for an out-of-range
# calendar field (e.g. month 99, hour 25). _IMPLICIT_TIMESTAMP (the RESOLVER
# pattern) is byte-identical to PyYAML's resolver, so anything it tags is also
# tagged by PyYAML and re-matched here.
_TIMESTAMP_CONSTRUCT = re.compile(
r"""^(?P<year>[0-9][0-9][0-9][0-9])
-(?P<month>[0-9][0-9]?)
-(?P<day>[0-9][0-9]?)
(?:(?:[Tt]|[ \t]+)
(?P<hour>[0-9][0-9]?)
:(?P<minute>[0-9][0-9])
:(?P<second>[0-9][0-9])
(?:\.(?P<fraction>[0-9]*))?
(?:[ \t]*(?P<tz>Z|(?P<tz_sign>[-+])(?P<tz_hour>[0-9][0-9]?)
(?::(?P<tz_minute>[0-9][0-9]))?))?)?$""",
re.X,
)
def _int_constructible(text):
# Replicate PyYAML SafeConstructor.construct_yaml_int and report whether it
# would succeed. A resolver-tagged int whose radix body is empty after
# underscore removal (e.g. "0b_", "0x_", "0x__") makes int(base) raise, so
# PyYAML fails the WHOLE document -> the fallback must fail closed too.
value = text.replace("_", "")
if value[:1] in ("+", "-"):
value = value[1:]
if value == "0":
return True
try:
if value.startswith("0b"):
int(value[2:], 2)
elif value.startswith("0x"):
int(value[2:], 16)
elif value[:1] == "0":
int(value, 8)
elif ":" in value:
[int(part) for part in value.split(":")]
else:
int(value)
except ValueError:
return False
return True
def _float_constructible(text):
# Replicate PyYAML SafeConstructor.construct_yaml_float. Retained for the
# WHOLE-document invariant even though PyYAML's float-tagged set is always
# float()-constructible: the fallback's float RESOLVER pattern is a strict
# superset of PyYAML's (it also matches unsigned-exponent spellings PyYAML
# keeps as strings), and every such extra is likewise constructible, so this
# never fails closed where PyYAML would emit a token.
value = text.replace("_", "").lower()
if value[:1] in ("+", "-"):
value = value[1:]
if value in (".inf", ".nan"):
return True
try:
if ":" in value:
[float(part) for part in value.split(":")]
else:
float(value)
except ValueError:
return False
return True
def _timestamp_constructible(text):
# Replicate PyYAML SafeConstructor.construct_yaml_timestamp: build the same
# datetime.date/datetime and report whether it raises. Returns False for an
# out-of-range calendar field (month/day/hour/...), matching PyYAML's
# whole-document ValueError.
match = _TIMESTAMP_CONSTRUCT.match(text)
if not match:
return False
values = match.groupdict()
try:
year = int(values["year"])
month = int(values["month"])
day = int(values["day"])
if not values["hour"]:
datetime.date(year, month, day)
return True
hour = int(values["hour"])
minute = int(values["minute"])
second = int(values["second"])
fraction = 0
if values["fraction"]:
frac = values["fraction"][:6]
frac += "0" * (6 - len(frac))
fraction = int(frac)
tzinfo = None
if values["tz_sign"]:
tz_hour = int(values["tz_hour"])
tz_minute = int(values["tz_minute"] or 0)
delta = datetime.timedelta(hours=tz_hour, minutes=tz_minute)
if values["tz_sign"] == "-":
delta = -delta
tzinfo = datetime.timezone(delta)
elif values["tz"]:
tzinfo = datetime.timezone.utc
datetime.datetime(
year, month, day, hour, minute, second, fraction, tzinfo=tzinfo
)
except (ValueError, OverflowError):
return False
return True
def _constructible(text):
# WHOLE-DOCUMENT INVARIANT: the fallback resolves the SAME login token as
# PyYAML safe_load or fails closed -- never less conservative -- INCLUDING
# when PyYAML raises a CONSTRUCTOR error anywhere in the document. A plain
# scalar can match a typed implicit resolver (int/float/timestamp) yet NOT be
# constructible (e.g. 2023-99-99, 0b_, 0x_); PyYAML then raises on the whole
# load and yields no token, so the fallback MUST fail closed for the whole
# document too. This returns True only when PyYAML's constructor would build
# the scalar (null/bool token sets are always constructible), else False so
# the caller fails closed. `text` is assumed to satisfy _implicit_nonstring.
if _IMPLICIT_NULL.match(text) or _IMPLICIT_BOOL.match(text):
return True
if _IMPLICIT_TIMESTAMP.match(text):
return _timestamp_constructible(text)
if _IMPLICIT_INT.match(text):
return _int_constructible(text)
if _IMPLICIT_FLOAT.match(text):
return _float_constructible(text)
return True
# Sentinel: "outside the supported subset -> fail closed". Distinct from a
# genuine null (None), which is a valid resolved value.
_FAIL = object()
# Separators are SPACE-only: PyYAML rejects a tab used as key/value whitespace
# (before or after the ':') with a scanner error, so a tab there must NOT be
# treated as a benign separator. Space before the colon and one space after it
# stay valid (PyYAML strips a plain key's trailing spaces); a tab in either
# position makes the whole line fail to match -> the caller fails closed.
_KEY_RE = re.compile(r"^([A-Za-z0-9_][A-Za-z0-9_.\-]*) *:(?:[ ](.*)|)$")
_FLOW = set("[]{}*&!")
class _Bail(Exception):
# Raised the instant the document leaves the narrow tea-config subset this
# recognizer can prove it resolves IDENTICALLY to PyYAML. Caught by
# _safe_parse, which then fails closed (returns _FAIL) rather than guess.
pass
def _scalar(raw):
# Resolve a single flow scalar (quoted or plain) the way PyYAML would for
# tea's simple values, or _FAIL when it is outside the supported subset so
# the caller fails closed instead of guessing.
#
# A quoted scalar is ALWAYS a string (its contents returned verbatim); a '#'
# inside quotes is data. An UNQUOTED scalar ends at the first whitespace
# -preceded '#' (a YAML comment must be preceded by whitespace or line start,
# so "abc#def" stays literal while "abc # note" becomes "abc"), and is then
# subject to PyYAML's implicit typing: forms like 12345 / null / ~ / yes /
# 3.14 / a timestamp resolve to a NON-string (int/None/bool/float/date), so
# they return None here (PyYAML's path rejects a non-str token via _accept).
# Strip SPACES only, never tabs: PyYAML raises a scanner error on a tab in a
# plain/leading/trailing scalar position, so a tab must be PRESERVED here to
# trip the fail-closed guard below rather than be silently normalized away.
value = raw.strip(" ")
if not value:
return None # empty plain scalar -> null
if value[0] in ("'", '"'):
quote = value[0]
end = value.find(quote, 1)
if end == -1:
return _FAIL # unterminated quote: PyYAML would error / continue
rest = value[end + 1:].strip(" ")
if rest and not rest.startswith("#"):
return _FAIL # trailing junk after a quoted scalar
inner = value[1:end]
# Single-quote '' escaping and double-quote backslash escapes are NOT
# interpreted here; reject any scalar that uses them so we never diverge
# from PyYAML on escape handling.
if quote == "'" and "'" in inner:
return _FAIL
if quote == '"' and "\\" in inner:
return _FAIL
return inner
for i, ch in enumerate(value):
if ch == "#" and (i == 0 or value[i - 1] in (" ", "\t")):
value = value[:i]
break
value = value.strip(" ") # spaces only; a tab must survive to fail closed
if not value:
return None
if value[0] in _FLOW or value[0] in ("|", ">", "?", "@", "`", '"', "'", "%", ","):
return _FAIL # flow / block-scalar / reserved / directive / anchor / quote
if value[0] in ("-", "?", ":") and (len(value) == 1 or value[1] in (" ", "\t")):
# A bare block indicator, not a plain scalar: '-'/'- ' opens a sequence
# entry, '?'/'? ' a complex mapping key, ':'/': ' a mapping value -- all
# illegal in a value position, where PyYAML raises a scanner error on the
# whole document. "-x"/"-1"/"?x"/":x" (indicator NOT followed by space)
# remain valid plain scalars and fall through. Fail closed on the bare
# indicator so the fallback never emits a token PyYAML would refuse.
return _FAIL
if any(ch in _FLOW for ch in value):
return _FAIL
if "\t" in value:
# A tab anywhere in a plain scalar (leading, trailing, or embedded) is a
# PyYAML scanner error on the whole document -- it accepts tabs ONLY
# inside quoted scalars (handled above, returned verbatim). Fail closed
# so the fallback never emits a token PyYAML would refuse over a tab.
return _FAIL
if ": " in value or value.endswith(":"):
return _FAIL # nested-mapping-in-scalar / ambiguous
if _implicit_nonstring(value):
# A plain scalar PyYAML would tag as a non-string (null/bool/int/float/
# timestamp). If PyYAML's CONSTRUCTOR would build it, the value is a
# non-string -> null-equivalent for a token field: return None and keep
# parsing (as before). But if it matches a typed implicit resolver yet is
# NOT constructible (e.g. 2023-99-99, 0b_, 0x_), PyYAML raises on the
# WHOLE document and yields no token, so the fallback MUST fail closed
# for the whole document too -> _FAIL (which the caller turns into _Bail).
if not _constructible(value):
return _FAIL
return None
return value
class _Parser:
# A deliberately NARROW, conservative recognizer for the block-style YAML
# subset tea writes (mappings of scalar fields; a `logins:` block SEQUENCE of
# such mappings; optional shallow nested mappings for e.g. preferences). It
# reconstructs the SAME Python object PyYAML's SafeLoader would, but the
# instant it meets anything it cannot prove it handles identically -- a
# document marker (--- / ...), a block scalar (| / >), a flow collection, a
# duplicate mapping key, inconsistent indentation, an escape, or any line
# outside the grammar -- it raises _Bail so the whole resolution fails
# closed. This guarantees the module invariant (only ever MORE conservative
# than PyYAML, never less) at the DOCUMENT level, closing the structural
# fail-open classes (nested-logins shadow, block-scalar shadow, duplicate
# root key, malformed-after-valid, and extra-document) that a line scan that
# does not validate whole-document structure would miss.
def __init__(self, lines):
self.toks = []
for raw in lines:
if not raw.strip():
continue
lead = raw[: len(raw) - len(raw.lstrip(" \t"))]
if "\t" in lead:
raise _Bail() # tab in indentation: PyYAML scanner error
indent = len(lead)
body = raw[indent:]
if body.lstrip().startswith("#"):
continue
if re.match(r"^(---|\.\.\.)(\s|$)", body) or body in ("---", "..."):
raise _Bail() # document / end marker -> multi-doc -> fail closed
# rstrip SPACES only: a trailing tab is a PyYAML scanner error, so it
# must be kept on the token body to reach the fail-closed guards
# (rstrip() would swallow it and let a bad line resolve a token).
self.toks.append((indent, body.rstrip(" ")))
self.i = 0
def peek(self):
return self.toks[self.i] if self.i < len(self.toks) else None
def parse_document(self):
if not self.toks:
return None
node = self.parse_node(0)
if self.i != len(self.toks):
raise _Bail() # trailing unconsumed content -> malformed
return node
def parse_node(self, min_indent):
tok = self.peek()
if tok is None:
return None
indent, body = tok
if indent < min_indent:
return None
if body.startswith("-") and (len(body) == 1 or body[1] in (" ", "\t")):
return self.parse_seq(indent)
return self.parse_map(indent)
def parse_map(self, indent):
result = {}
while True:
tok = self.peek()
if tok is None:
break
cur_indent, body = tok
if cur_indent < indent:
break
if cur_indent > indent:
raise _Bail() # unexpected deeper line (bad indentation)
if body.startswith("-") and (len(body) == 1 or body[1] in (" ", "\t")):
raise _Bail() # sequence item where a mapping entry was expected
m = _KEY_RE.match(body)
if not m:
raise _Bail()
key = m.group(1)
inline = m.group(2)
self.i += 1
if key in result:
raise _Bail() # duplicate mapping key (PyYAML last-wins; we bail)
if inline is not None and inline.strip(" ") != "":
val = _scalar(inline)
if val is _FAIL:
raise _Bail()
result[key] = val
else:
result[key] = self.parse_block_value(indent)
return result
def parse_block_value(self, key_indent):
# The value after a "key:" with no inline scalar. A block SEQUENCE may sit
# at the same indent as the key (YAML permits `- ` aligned with the key --
# tea's own on-disk shape) or deeper; a block MAPPING must be strictly
# deeper; otherwise the value is null.
nxt = self.peek()
if nxt is None:
return None
ni, nb = nxt
is_item = nb.startswith("-") and (len(nb) == 1 or nb[1] in (" ", "\t"))
if is_item and ni >= key_indent:
return self.parse_seq(ni)
if ni > key_indent:
return self.parse_node(ni)
return None
def parse_seq(self, indent):
result = []
while True:
tok = self.peek()
if tok is None:
break
cur_indent, body = tok
if cur_indent < indent:
break
if cur_indent > indent:
raise _Bail()
if not (body.startswith("-") and (len(body) == 1 or body[1] in (" ", "\t"))):
break # a mapping entry at this indent ends the sequence
rest = body[1:].strip(" ") # spaces only; a tab must survive to bail
self.i += 1
if rest == "":
nxt = self.peek()
if nxt is not None and nxt[0] > indent:
result.append(self.parse_node(indent + 1))
else:
result.append(None)
continue
km = _KEY_RE.match(rest)
if km:
# "- key: value" opens a mapping whose fields continue at the
# column where the content after the dash began.
field_indent = indent + (len(body) - len(body[1:].lstrip()))
result.append(self.parse_inline_map(field_indent, km))
else:
val = _scalar(rest)
if val is _FAIL:
raise _Bail()
result.append(val)
return result
def parse_inline_map(self, field_indent, first_match):
result = {}
key = first_match.group(1)
inline = first_match.group(2)
if inline is not None and inline.strip(" ") != "":
val = _scalar(inline)
if val is _FAIL:
raise _Bail()
result[key] = val
else:
result[key] = self.parse_block_value(field_indent)
while True:
tok = self.peek()
if tok is None:
break
cur_indent, body = tok
if cur_indent != field_indent:
if cur_indent > field_indent:
raise _Bail()
break
if body.startswith("-") and (len(body) == 1 or body[1] in (" ", "\t")):
raise _Bail()
m = _KEY_RE.match(body)
if not m:
raise _Bail()
k = m.group(1)
iv = m.group(2)
self.i += 1
if k in result:
raise _Bail()
if iv is not None and iv.strip(" ") != "":
v = _scalar(iv)
if v is _FAIL:
raise _Bail()
result[k] = v
else:
result[k] = self.parse_block_value(field_indent)
return result
def _safe_parse(lines):
# Return the parsed root object (dict/list/scalar/None) when the WHOLE
# document is inside the supported subset, else _FAIL (fail closed).
try:
return _Parser(lines).parse_document()
except _Bail:
return _FAIL
except Exception:
return _FAIL
def _url_matches_repo_host(url):
# Mirror gitea_url_matches_host (detect-platform.sh): the login's recorded
# URL must name the SAME host AND the SAME effective port as the repo remote
# host, not merely the same hostname. A login configured for an explicit,
# non-default provider port (e.g. :9443) must NOT satisfy a portless (default
# -port) repo host, and a login on the matching port (e.g. :8443) must NOT be
# rejected. Ports are normalized by applying the login URL's scheme default
# (80 for http, else 443) to whichever side omits the port, symmetrically, so
# an implicit port and its explicit default-port form compare equal.
if not isinstance(url, str) or not url:
return False
configured = urlparse(url if "//" in url else f"//{url}")
remote = urlparse(f"//{repo_host}")
configured_host = configured.hostname
if not configured_host or configured_host.lower() != (remote.hostname or "").lower():
return False
default_port = 80 if configured.scheme == "http" else 443
configured_port = configured.port if configured.port is not None else default_port
remote_port = remote.port if remote.port is not None else default_port
return configured_port == remote_port
def _accept(token, url):
# Enforce the host bind before surfacing a token. When a repo host is given,
# the login's recorded URL host AND port must match it; a login with no
# usable URL (or a mismatched host/port) is rejected (fail closed) so a
# cross-host (or cross-port) credential is never emitted.
if not isinstance(token, str) or not token:
return None
if repo_host:
if not _url_matches_repo_host(url):
return None
return token
def _token_via_pyyaml():
# Preferred, fully general path when PyYAML is installed. Raises ImportError
# (caught by the caller) when the module is unavailable so the environment
# -robust fallback can take over instead of failing closed on every host
# that lacks PyYAML.
import yaml
with open(config_path, encoding="utf-8") as handle:
config = yaml.safe_load(handle)
logins = config.get("logins") if isinstance(config, dict) else None
if not isinstance(logins, list):
return None
for login in logins:
if isinstance(login, dict) and str(login.get("name") or "") == wanted:
return _accept(login.get("token"), login.get("url"))
return None
def _token_via_lines():
# Conservative fallback for hosts without PyYAML. It parses config.yml with a
# strict recognizer (_safe_parse) of the narrow block-style subset tea writes,
# which reconstructs the SAME object PyYAML would OR fails closed (_FAIL) on
# ANYTHING it cannot prove it resolves identically -- document markers, block
# scalars, flow collections, duplicate keys, inconsistent indentation, or any
# line outside the grammar. On a recognized document it then resolves the
# login EXACTLY as the PyYAML path does (root `logins` list -> first entry
# whose `name` equals the request -> host/port-bound token), so the fallback
# can only ever be MORE conservative than PyYAML, never less.
with open(config_path, encoding="utf-8") as handle:
lines = handle.read().splitlines()
config = _safe_parse(lines)
if config is _FAIL:
return None
logins = config.get("logins") if isinstance(config, dict) else None
if not isinstance(logins, list):
return None
for login in logins:
if isinstance(login, dict) and str(login.get("name") or "") == wanted:
return _accept(login.get("token"), login.get("url"))
return None
try:
try:
token = _token_via_pyyaml()
except ImportError:
token = _token_via_lines()
except Exception:
raise SystemExit(1)
if isinstance(token, str) and token:
print(token)
raise SystemExit(0)
raise SystemExit(1)
PY
}
# Resolve HTTPS basic auth credentials for a Gitea host from ~/.git-credentials.
# Prints "username:password" for direct curl -u consumption. Callers must not log it.
get_gitea_basic_auth() {
local host="$1"
local creds="$HOME/.git-credentials"
if [[ ! -f "$creds" ]]; then
return 1
fi
python3 - "$host" "$creds" <<'PY'
import sys
from pathlib import Path
from urllib.parse import unquote, urlparse
host = sys.argv[1]
creds = Path(sys.argv[2])
for line in creds.read_text(encoding="utf-8").splitlines():
parsed = urlparse(line.strip())
if parsed.hostname != host:
continue
username = unquote(parsed.username or "")
password = unquote(parsed.password or "")
if username and password:
print(f"{username}:{password}")
raise SystemExit(0)
raise SystemExit(1)
PY
}
# If script is run directly (not sourced), output the platform
if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
detect_platform
fi