chtypes 2.0.0.dev8__py3-none-any.whl → 2.0.0.dev9__py3-none-any.whl

chtypes/_decode.py

@@ -431,8 +431,9 @@ def decode_batch(raw: bytes, export: bytes | None) -> BatchResult:
     export_declined = _bytes(obj, "export_declined", where)
     if export_declined:
         # A declined export has no payload and no spans, whatever buffer the call
-        # returned: the library may hand back a zero-length one, so the document's
-        # export_declined decides, never the buffer's length.
+        # returned: the library returns a NULL out_export for it (builds up to
+        # 20261011.105019 returned a zero-length buffer), and the document's
+        # export_declined decides, never the buffer.
         export, spans = None, None
     return BatchResult(
         outcome=Outcome.of(_text(obj, "outcome", where)),

chtypes/_input.py

@@ -45,6 +45,31 @@ def body_bytes(value: bytes, what: str = "body") -> bytes:
     raise TypeError(f"{what} must be bytes, not {type(value).__name__}")
 
 
+_NON_UTF8_HINT = (
+    "this ABI generation cannot carry a non-UTF-8 value in a JSON input; "
+    "write the bytes as unhex('<hex>') in the expression instead"
+)
+
+
+def _is_utf8(text: str) -> bool:
+    """False for a `str` that cannot be UTF-8 encoded (a lone surrogate, as
+    `surrogateescape` makes of undecodable bytes)."""
+    try:
+        text.encode("utf-8")
+    except UnicodeEncodeError:
+        return False
+    return True
+
+
+def _refuse_non_utf8(what: str, part: str, key: str) -> Exception:
+    # The key is shown escaped (ASCII only), never as the raw text.
+    return misuse(
+        f"{what}: the key {json.dumps(key)} is not valid UTF-8, and {_NON_UTF8_HINT}"
+        if part == "key"
+        else f"{what}: the value for key {json.dumps(key)} is not valid UTF-8, and {_NON_UTF8_HINT}"
+    )
+
+
 def _string_map(mapping: Mapping[str, str], what: str) -> dict[str, str]:
     out: dict[str, str] = {}
     for key, value in mapping.items():
@@ -53,6 +78,12 @@ def _string_map(mapping: Mapping[str, str], what: str) -> dict[str, str]:
                 f"{what} maps strings to strings only; got {type(key).__name__} -> "
                 f"{type(value).__name__} for {key!r} (a value is never rewritten)"
             )
+        # json.dumps would write a lone surrogate as a \udXXX escape, a value
+        # the library does not read as the bytes the caller meant: refuse.
+        if not _is_utf8(key):
+            raise _refuse_non_utf8(what, "key", key)
+        if not _is_utf8(value):
+            raise _refuse_non_utf8(what, "value", key)
         out[key] = value
     return out
 
@@ -75,6 +106,8 @@ def settings_json(
     if session_timezone is not None:
         if not isinstance(session_timezone, str):
             raise TypeError(f"session_timezone must be str, not {type(session_timezone).__name__}")
+        if not _is_utf8(session_timezone):
+            raise misuse(f"the zone: the value is not valid UTF-8, and {_NON_UTF8_HINT}")
         if _ZONE_KEY in merged:
             raise misuse(
                 f"the {_ZONE_KEY} option and a {_ZONE_KEY} settings key were both given; "
@@ -141,10 +174,12 @@ def server_profile_json(profile: ServerProfile) -> bytes:
     if profile.timezone is not None:
         if not isinstance(profile.timezone, str):
             raise TypeError(f"timezone must be str, not {type(profile.timezone).__name__}")
+        if not _is_utf8(profile.timezone):
+            raise misuse(f"server profile: the timezone is not valid UTF-8, and {_NON_UTF8_HINT}")
         if profile.timezone != "":
             doc["timezone"] = profile.timezone
     if profile.settings is not None:
-        doc["settings"] = _string_map(profile.settings, "settings")
+        doc["settings"] = _string_map(profile.settings, "server profile settings")
     if profile.macros is not None:
-        doc["macros"] = _string_map(profile.macros, "macros")
+        doc["macros"] = _string_map(profile.macros, "server profile macros")
     return _dump(doc)

chtypes/library.py

@@ -296,7 +296,7 @@ class Schema(_Handle):
         zone is its own, fixed here: its WHERE runs in the session this call's
         `session_timezone` (or `settings`) names, on every evaluation."""
         expr_bytes = to_bytes(expr, "expr")
-        params_bytes = string_map_json(params, "params")
+        params_bytes = string_map_json(params, "query parameters")
         settings_bytes = settings_json(settings, session_timezone)
         with _hold(self._guard):
             handle = self._library._api.filter_create(

{chtypes-2.0.0.dev8.dist-info → chtypes-2.0.0.dev9.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: chtypes
-Version: 2.0.0.dev8
+Version: 2.0.0.dev9
 Summary: Python binding for the chtypes artifacts: ClickHouse's own type system, per version, behind the frozen chs_* C ABI
 Project-URL: Homepage, https://github.com/wave-rf/chtypes
 Project-URL: Repository, https://github.com/wave-rf/chtypes

{chtypes-2.0.0.dev8.dist-info → chtypes-2.0.0.dev9.dist-info}/RECORD

@@ -1,13 +1,13 @@
 chtypes/__init__.py,sha256=nYd9hTbAU8ffzVj5mYqUAEWxzfYg-67zW_h0j5XasMA,6187
 chtypes/__main__.py,sha256=mrpF3Cf0_l-ODhqVzrN8JwwjG64glJ__Soehs6-ALu8,18081
 chtypes/_codes.py,sha256=yiLLEiJDJ20WseyFZE1VzlqSiL9J8GC8JMj8tKXCZss,1238
-chtypes/_decode.py,sha256=NV5IgBsAJuEqYD5u2SBZIlDSQnAe4t_ckSBRAG0x1jM,23208
+chtypes/_decode.py,sha256=ta2D6gDu6JOxYacypT5emt3MCdWp5gCZlcyPz0k1Dzo,23272
 chtypes/_ed25519.py,sha256=uwaAKWvgoc936e1ZfgLrtR47W87WWCL541kFaqBXrB0,4141
 chtypes/_guard.py,sha256=kVgvxRWu7H-eba3hTqPBmpqjxOCWdQGwiFAHvSnl1OU,1996
-chtypes/_input.py,sha256=VBNIUeDSEsq6EvgFW63UJt0kyAOSYJpb1nQOXvUQbOI,6031
+chtypes/_input.py,sha256=NczeJ6LR7gRc_dhgccv5zcrKlZ4nkh3wP0TBx5vHIbw,7468
 chtypes/_setup.py,sha256=7mXvPxLCHS9h1FRWNr5uKfCUg-Gk8VjmC-5KNW5HogI,6125
 chtypes/errors.py,sha256=uDs-M2NQpacoJK-LiWQDM_s5v_Jbm3tbyWduqvLgsyI,9410
-chtypes/library.py,sha256=G6DJFiRuv8--JARxfiSNEqeFLkafaMs_n9nG-IwoC74,17878
+chtypes/library.py,sha256=MurZz2CFLwm_lRMC_0X4SZNDNIlkwbdqKW7oFTl2XWc,17888
 chtypes/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 chtypes/registry.py,sha256=GozFQresMLLG0JmCD_rVtOgtNZzl9fgT0O7jQMsnHCE,21945
 chtypes/results.py,sha256=gue7f4pqnpvXlSteYqhmqU1ZuAYCD7p4AgTiuYWpgYY,12591
@@ -35,8 +35,8 @@ chtypes/_ocifetch/_referrers.py,sha256=J2b4gN6vryz_IzYHxrd2Tp-tQO9Cz766rZtKgCVcK
 chtypes/_ocifetch/_resolve.py,sha256=Qv8xFUdOR-Kb_JqmUeDiQ4_Xv2ETuNFpmoDckMp7eV8,11239
 chtypes/_ocifetch/_retired.py,sha256=MQ6nbWLJw50IZYY1VfM6AiCZ4BySK0GVkGVOtAXaq3Y,3060
 chtypes/_ocifetch/_unpack.py,sha256=Cn4-up63KL63L8pnkS5zwJ6VbbHPSigpCnmOdcHJ4RI,5609
-chtypes-2.0.0.dev8.dist-info/METADATA,sha256=IySGKPKxLdX-9HnkivYd1uK7-qQdwylgbljzw7XyNCs,11315
-chtypes-2.0.0.dev8.dist-info/WHEEL,sha256=W3fkpkm7-wf9vBI5Z-7s0eWkeM-spu78I8Neb98DeEg,87
-chtypes-2.0.0.dev8.dist-info/entry_points.txt,sha256=TdNcluWBR0VOt5mVFROsp-NiVPAdR3EHo0UsHlMC0r0,50
-chtypes-2.0.0.dev8.dist-info/licenses/LICENSE,sha256=z8d0m5b2O9McPEK1xHG_dWgUBT6EfBDz6wA0F7xSPTA,11358
-chtypes-2.0.0.dev8.dist-info/RECORD,,
+chtypes-2.0.0.dev9.dist-info/METADATA,sha256=AqDs8WwXXigXIHHi0XGvpM5IpTTJSC9vHqHwESJF0H8,11315
+chtypes-2.0.0.dev9.dist-info/WHEEL,sha256=W3fkpkm7-wf9vBI5Z-7s0eWkeM-spu78I8Neb98DeEg,87
+chtypes-2.0.0.dev9.dist-info/entry_points.txt,sha256=TdNcluWBR0VOt5mVFROsp-NiVPAdR3EHo0UsHlMC0r0,50
+chtypes-2.0.0.dev9.dist-info/licenses/LICENSE,sha256=z8d0m5b2O9McPEK1xHG_dWgUBT6EfBDz6wA0F7xSPTA,11358
+chtypes-2.0.0.dev9.dist-info/RECORD,,