Show the shape of a rejected wiki token in the error

When Gitea answers 401, add the token's length and likely storage mistakes
(masked text, NAME=value, quotes, whitespace) to the message, without any
character of the token, so a wrongly stored secret can be recognised from
the log.

Task: MIL-005#8

tests/test_publish_wiki.py

@@ -191,6 +191,57 @@ class TestMain:
         assert gitea.wiki == {"Home": b64("keep me")}
 
 
+class TestDescribeToken:
+    def test_recognises_a_gitea_token_shape(self):
+        description = publish_wiki.describe_token("a1b2c3d4e5" * 4)
+        assert "40 characters" in description
+        assert "looks like a Gitea token" in description
+
+    @pytest.mark.parametrize(
+        ("token", "expected"),
+        [
+            ("*******", "only mask characters"),
+            ("TOKEN_FOR_GITEA_WIKI=" + "a" * 40, "contains '='"),
+            ('"' + "a" * 40 + '"', "quote character"),
+            ("abc def", "whitespace"),
+        ],
+    )
+    def test_names_the_likely_mistake_without_echoing_the_token(self, token, expected):
+        description = publish_wiki.describe_token(token)
+        assert expected in description
+        assert token not in description
+
+
+class TestRejectedToken:
+    def test_rejection_adds_the_token_shape_but_not_the_token(self, monkeypatch, environment):
+        monkeypatch.setenv("WIKI_CREDENTIALS", "*******")
+
+        def reject(url, method="GET", headers=None, body=None):
+            raise publish_wiki.WorkflowError("credentials", "Gitea rejected the token.")
+
+        monkeypatch.setattr(publish_wiki, "request_json", reject)
+
+        with pytest.raises(publish_wiki.WorkflowError) as caught:
+            publish_wiki.main()
+
+        message = str(caught.value)
+        assert caught.value.category == "credentials"
+        assert "Token shape: 7 characters" in message
+        assert "only mask characters" in message
+        assert "*******" not in message.split("Token shape:")[0]
+
+    def test_other_categories_are_not_changed(self, monkeypatch, environment):
+        def forbid(url, method="GET", headers=None, body=None):
+            raise publish_wiki.WorkflowError("permissions", "Forbidden.")
+
+        monkeypatch.setattr(publish_wiki, "request_json", forbid)
+
+        with pytest.raises(publish_wiki.WorkflowError) as caught:
+            publish_wiki.main()
+
+        assert str(caught.value) == "[permissions] Forbidden."
+
+
 class TestRequestJson:
     @staticmethod
     def raise_http_error(monkeypatch, code, reason):

tools/publish_wiki.py

@@ -16,6 +16,7 @@ Exit codes: 0 published or nothing to do, 1 failed (message names a category).
 import base64
 import json
 import os
+import re
 import sys
 import urllib.error
 import urllib.parse
@@ -43,6 +44,7 @@ class WorkflowError(RuntimeError):
     def __init__(self, category: str, message: str) -> None:
         super().__init__(f"[{category}] {message}")
         self.category = category
+        self.detail = message
 
 
 def request_json(
@@ -110,6 +112,28 @@ def parse_gitea_token(raw_credentials: str | None) -> str:
     return token.strip()
 
 
+def describe_token(token: str) -> str:
+    """Describe the shape of a token without revealing any of its characters.
+
+    Used when Gitea rejects the token, so a wrongly stored secret (the masked
+    text, ``NAME=value``, quotes) can be recognised from the log.
+    """
+    facts = [f"{len(token)} characters"]
+    if re.fullmatch(r"[0-9a-f]{40}", token):
+        facts.append("looks like a Gitea token (40 hexadecimal characters)")
+        return ", ".join(facts)
+    facts.append("a Gitea token has 40 hexadecimal characters")
+    if set(token) <= {"*", "x", "X", "•"}:
+        facts.append("only mask characters: the masked text was stored")
+    if "=" in token:
+        facts.append("contains '=': the secret name may be part of the value")
+    if re.search(r"[\"'`]", token):
+        facts.append("contains a quote character")
+    if re.search(r"\s", token):
+        facts.append("contains whitespace")
+    return ", ".join(facts)
+
+
 def split_repository(full_name: str | None) -> tuple[str, str]:
     """Split ``owner/repo`` into its two parts."""
     owner, separator, repo = (full_name or "").partition("/")
@@ -218,6 +242,7 @@ def main() -> int:
         "Content-Type": "application/json",
     }
 
+    try:
         repository = request_json(repository_url, headers=headers)
         if isinstance(repository, dict) and repository.get("has_wiki") is False:
             raise WorkflowError(
@@ -227,6 +252,12 @@ def main() -> int:
         print("Preflight passed: Gitea accepted the token and the wiki is enabled.")
 
         result = publish(pages, f"{repository_url}/wiki", headers, request_json)
+    except WorkflowError as error:
+        if error.category == "credentials":
+            raise WorkflowError(
+                "credentials", f"{error.detail} Token shape: {describe_token(token)}."
+            ) from None
+        raise
     print(
         f"Published {len(pages)} page(s) to the wiki of {owner}/{repo}: "
         f"{len(result['created'])} created, {len(result['updated'])} updated, "