Parse every configuration entry without crossing assignment lines

great_ai/utilities/config_file/config_file.py

@@ -4,7 +4,7 @@ from typing import Dict, ItemsView, Iterator, KeysView, Mapping, Union, ValuesVi
 
 from ..logger.get_logger import get_logger
 from .parse_error import ParseError
-from .pattern import pattern
+from .pattern import ignored_line, pattern
 
 logger = get_logger("ConfigFile")
 
@@ -89,14 +89,25 @@ class ConfigFile(Mapping[str, str]):
         with open(self._path, encoding="utf-8") as f:
             lines: str = f.read()
 
-        matches = pattern.findall(lines)
-        for key, *values in matches:
-            try:
-                value = next(v for v in values if v)
-            except StopIteration:
-                raise ParseError(f"""Cannot parse config file ({
-                        self._path.absolute()
-                        }), error at key `{key}`""")
+        position = 0
+        while position < len(lines):
+            ignored = ignored_line.match(lines, position)
+            if ignored is not None and ignored.end() > position:
+                position = ignored.end()
+                continue
+            match = pattern.match(lines, position)
+            if match is None:
+                line = lines.count("\n", 0, position) + 1
+                raise ParseError(
+                    f"Cannot parse config file ({self._path.absolute()}) at line {line}"
+                )
+            position = match.end()
+            key = match.group("key")
+            value = next(
+                match.group(name)
+                for name in ("double", "single", "backtick", "bare")
+                if match.group(name) is not None
+            )
 
             already_exists = key in self._key_values
             if already_exists and not value.startswith(

great_ai/utilities/config_file/pattern.py

@@ -2,19 +2,16 @@ import re
 
 pattern = re.compile(
     r"""
-        (?:^|\n)        # new key-value pairs must start on a new line
-        \s*             # leading whitespace is allowed
-        (?!\#)          # the key cannot start with a `#` symbol
-        (\w+?)          # then comes the key
-        \s*=\s*         # the key and value are separated by an equal sign
-        (?:             # then comes the value
-              "([^"]*)"   # the value can be surrounded by quotes: "value"
-            | '([^']*)'   # the value can be surrounded by quotes: 'value'
-            | `([^`]*)`   # the value can be surrounded by quotes: `value`
-            | ([^#\n]*?)  # or it is bare, in that case, the trailing whitespace is ignored
+        [\t ]*(?P<key>\w+)[\t ]*=[\t ]*
+        (?:
+              "(?P<double>[^"]*)"
+            | '(?P<single>[^']*)'
+            | `(?P<backtick>[^`]*)`
+            | (?!["'`])(?P<bare>[^\#\r\n]*?)
         )
-        \s*(?:\#.*)?    # comments can be added with the `#` symbol
-        (?=\n|$)        # a key-value pairs are separated by new lines
+        [\t ]*(?:\#[^\r\n]*)?(?:\r?\n|$)
     """,
     flags=re.UNICODE | re.VERBOSE,
 )
+
+ignored_line = re.compile(r"[\t ]*(?:\#[^\r\n]*)?(?:\r?\n|$)")

tests/utilities/test_config_file.py

@@ -2,7 +2,7 @@ import os
 from pathlib import Path
 
 import pytest
-from great_ai.utilities import ConfigFile
+from great_ai.utilities import ConfigFile, ParseError
 
 DATA_PATH = Path(__file__).parent.resolve() / "data"
 
@@ -88,3 +88,25 @@ def test_env_exists_ignore_fallback() -> None:
 def test_duplicate_key() -> None:
     with pytest.raises(KeyError):
         ConfigFile(DATA_PATH / "bad.conf")
+
+
+def test_empty_values_do_not_consume_the_next_assignment(tmp_path: Path) -> None:
+    path = tmp_path / "empty.conf"
+    path.write_text('empty=\nquoted=""\nnext=value\nmultiline="a\nb"\n')
+    assert dict(ConfigFile(path)) == {
+        "empty": "",
+        "quoted": "",
+        "next": "value",
+        "multiline": "a\nb",
+    }
+
+
+@pytest.mark.parametrize(
+    "content",
+    ["broken syntax\nkey=value\n", 'key="unterminated\n', 'key="value" trailing\n'],
+)
+def test_malformed_configuration_is_rejected(tmp_path: Path, content: str) -> None:
+    path = tmp_path / "malformed.conf"
+    path.write_text(content)
+    with pytest.raises(ParseError):
+        ConfigFile(path)