markback 0.1.1__py3-none-any.whl → 0.1.3__py3-none-any.whl

markback/linter.py

@@ -137,6 +137,67 @@ def lint_prior_exists(
     return diagnostics
 
 
+def _is_position_invalid(source_ref) -> tuple[bool, str]:
+    """Check if a SourceRef has an invalid position range.
+
+    Returns (is_invalid, error_message).
+    Position is invalid if:
+    - end_line < start_line
+    - end_line == start_line and end_column < start_column
+    """
+    if source_ref.start_line is None or source_ref.end_line is None:
+        return False, ""
+
+    if source_ref.end_line < source_ref.start_line:
+        return True, f"end line {source_ref.end_line} is less than start line {source_ref.start_line}"
+
+    if source_ref.end_line == source_ref.start_line:
+        if (source_ref.start_column is not None and
+            source_ref.end_column is not None and
+            source_ref.end_column < source_ref.start_column):
+            return True, f"end column {source_ref.end_column} is less than start column {source_ref.start_column} on line {source_ref.start_line}"
+
+    return False, ""
+
+
+def lint_line_range(
+    record: Record,
+    record_idx: int,
+) -> list[Diagnostic]:
+    """Check if line/character ranges are valid (end position >= start position)."""
+    diagnostics: list[Diagnostic] = []
+
+    # Check @source range
+    if record.source and record.source.start_line is not None:
+        is_invalid, error_msg = _is_position_invalid(record.source)
+        if is_invalid:
+            diagnostics.append(Diagnostic(
+                file=record._source_file,
+                line=record._start_line,
+                column=None,
+                severity=Severity.ERROR,
+                code=ErrorCode.E011,
+                message=f"Invalid range in @source: {error_msg}",
+                record_index=record_idx,
+            ))
+
+    # Check @prior range
+    if record.prior and record.prior.start_line is not None:
+        is_invalid, error_msg = _is_position_invalid(record.prior)
+        if is_invalid:
+            diagnostics.append(Diagnostic(
+                file=record._source_file,
+                line=record._start_line,
+                column=None,
+                severity=Severity.ERROR,
+                code=ErrorCode.E011,
+                message=f"Invalid range in @prior: {error_msg}",
+                record_index=record_idx,
+            ))
+
+    return diagnostics
+
+
 def lint_canonical_format(
     records: list[Record],
     original_text: str,
@@ -206,6 +267,9 @@ def lint_string(
             result.diagnostics.extend(lint_source_exists(record, base_path, idx))
             result.diagnostics.extend(lint_prior_exists(record, base_path, idx))
 
+        # Check line range validity
+        result.diagnostics.extend(lint_line_range(record, idx))
+
     # Check canonical format
     if check_canonical and result.records and not result.has_errors:
         result.diagnostics.extend(lint_canonical_format(

markback/parser.py

@@ -17,7 +17,7 @@ from .types import (
 
 
 # Known header keywords
-KNOWN_HEADERS = {"uri", "source", "prior"}
+KNOWN_HEADERS = {"uri", "by", "source", "prior"}
 
 # Patterns
 HEADER_PATTERN = re.compile(r"^@([a-z]+)\s+(.+)$")
@@ -145,6 +145,7 @@ def parse_string(
         nonlocal pending_uri, in_content, had_blank_line
 
         uri = current_headers.get("uri") or pending_uri
+        by = current_headers.get("by")
         source_str = current_headers.get("source")
         source = SourceRef(source_str) if source_str else None
         prior_str = current_headers.get("prior")
@@ -164,6 +165,7 @@ def parse_string(
         record = Record(
             feedback=feedback,
             uri=uri,
+            by=by,
             source=source,
             prior=prior,
             content=content,
@@ -242,14 +244,16 @@ def parse_string(
                     line_num,
                 )
 
-            # Use any pending @uri from previous line and @prior if present
+            # Use any pending @uri from previous line and @by, @prior if present
             uri = pending_uri or current_headers.get("uri")
+            by = current_headers.get("by")
             prior_str = current_headers.get("prior")
             prior = SourceRef(prior_str) if prior_str else None
 
             record = Record(
                 feedback=feedback or "",
                 uri=uri,
+                by=by,
                 source=source,
                 prior=prior,
                 content=None,

markback/types.py

@@ -1,5 +1,6 @@
 """Core types for MarkBack format."""
 
+import re
 from dataclasses import dataclass, field
 from enum import Enum
 from pathlib import Path
@@ -25,6 +26,7 @@ class ErrorCode(Enum):
     E008 = "E008"  # Unclosed quote in structured attribute value
     E009 = "E009"  # Empty feedback (nothing after <<< )
     E010 = "E010"  # Missing blank line before inline content
+    E011 = "E011"  # Invalid line range (end < start)
 
 
 class WarningCode(Enum):
@@ -76,29 +78,90 @@ class Diagnostic:
         }
 
 
+# Regex to parse line/character range from a path
+# Supports: path:line, path:line:col, path:line-line, path:line:col-line:col
+_LINE_RANGE_PATTERN = re.compile(r'^(.+?):(\d+)(?::(\d+))?(?:-(\d+)(?::(\d+))?)?$')
+
+
 @dataclass
 class SourceRef:
     """Reference to external content (file path or URI)."""
     value: str
     is_uri: bool = False
+    start_line: Optional[int] = None
+    end_line: Optional[int] = None
+    start_column: Optional[int] = None
+    end_column: Optional[int] = None
+    _path_only: str = ""
 
     def __post_init__(self):
-        # Determine if this is a URI or file path
+        # Parse line range if present
+        self._parse_line_range()
+
+        # Determine if this is a URI or file path (using path without line range)
         if not self.is_uri:
-            parsed = urlparse(self.value)
+            parsed = urlparse(self._path_only)
             # Consider it a URI if it has a scheme that's not a Windows drive letter
             self.is_uri = bool(parsed.scheme) and len(parsed.scheme) > 1
 
+    def _parse_line_range(self):
+        """Parse optional line/character range from value."""
+        match = _LINE_RANGE_PATTERN.match(self.value)
+        if match:
+            self._path_only = match.group(1)
+            self.start_line = int(match.group(2))
+            if match.group(3):
+                self.start_column = int(match.group(3))
+            if match.group(4):
+                self.end_line = int(match.group(4))
+                if match.group(5):
+                    self.end_column = int(match.group(5))
+            else:
+                # Single line/position reference: start and end are the same
+                self.end_line = self.start_line
+                self.end_column = self.start_column
+        else:
+            self._path_only = self.value
+
+    @property
+    def path(self) -> str:
+        """Return path without line range."""
+        return self._path_only
+
+    @property
+    def line_range_str(self) -> Optional[str]:
+        """Return formatted line/character range string, or None if no range."""
+        if self.start_line is None:
+            return None
+
+        # Build start position
+        if self.start_column is not None:
+            start = f":{self.start_line}:{self.start_column}"
+        else:
+            start = f":{self.start_line}"
+
+        # Check if end is the same as start (single position)
+        if self.start_line == self.end_line and self.start_column == self.end_column:
+            return start
+
+        # Build end position
+        if self.end_column is not None:
+            end = f"-{self.end_line}:{self.end_column}"
+        else:
+            end = f"-{self.end_line}"
+
+        return f"{start}{end}"
+
     def resolve(self, base_path: Optional[Path] = None) -> Path:
         """Resolve to a file path (relative paths resolved against base_path)."""
         if self.is_uri:
-            parsed = urlparse(self.value)
+            parsed = urlparse(self._path_only)
             if parsed.scheme == "file":
                 # file:// URI
                 return Path(parsed.path)
             raise ValueError(f"Cannot resolve non-file URI to path: {self.value}")
 
-        path = Path(self.value)
+        path = Path(self._path_only)
         if path.is_absolute():
             return path
         if base_path:
@@ -122,6 +185,7 @@ class Record:
     """A MarkBack record containing content and feedback."""
     feedback: str
     uri: Optional[str] = None
+    by: Optional[str] = None
     source: Optional[SourceRef] = None
     prior: Optional[SourceRef] = None
     content: Optional[str] = None
@@ -155,6 +219,7 @@ class Record:
         """Convert to JSON-serializable dict."""
         return {
             "uri": self.uri,
+            "by": self.by,
             "source": str(self.source) if self.source else None,
             "prior": str(self.prior) if self.prior else None,
             "content": self.content,

markback/writer.py

@@ -38,17 +38,21 @@ def write_record_canonical(
     )
 
     if use_compact:
-        # Compact format: @uri on its own line (if present), then @prior, then @source ... <<<
+        # Compact format: @uri, @by, @prior on own lines (if present), then @source ... <<<
         if record.uri:
             lines.append(f"@uri {record.uri}")
+        if record.by:
+            lines.append(f"@by {record.by}")
         if record.prior:
             lines.append(f"@prior {record.prior}")
         lines.append(f"@source {record.source} <<< {record.feedback}")
     else:
         # Full format
-        # Headers: @uri first, then @prior, then @source
+        # Headers: @uri first, then @by, then @prior, then @source
         if record.uri:
             lines.append(f"@uri {record.uri}")
+        if record.by:
+            lines.append(f"@by {record.by}")
         if record.prior:
             lines.append(f"@prior {record.prior}")
         if record.source:
@@ -151,7 +155,10 @@ def write_label_file(record: Record) -> str:
 
     if record.uri:
         lines.append(f"@uri {record.uri}")
-    
+
+    if record.by:
+        lines.append(f"@by {record.by}")
+
     if record.prior:
         lines.append(f"@prior {record.prior}")
 

{markback-0.1.1.dist-info → markback-0.1.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: markback
-Version: 0.1.1
+Version: 0.1.3
 Summary: A compact, human-writable format for storing content paired with feedback/labels
 Project-URL: Homepage, https://github.com/dandriscoll/markback
 Project-URL: Repository, https://github.com/dandriscoll/markback

markback-0.1.3.dist-info/RECORD

@@ -0,0 +1,14 @@
+markback/__init__.py,sha256=B0-2dpUu5nkbnUI0hPz-x7PHiOl7M-tiRi6s3UCYJFk,1540
+markback/cli.py,sha256=5wMk1OUG7W_voS9DxeFxRJrBTMabEdOK_s_o3Irxuu0,13639
+markback/config.py,sha256=eTVhb7UwDER9FRYo8QUAvneLHSqXD2ZtLUgtBtnljUs,5455
+markback/linter.py,sha256=vKy5JHTEGspF4-lWRL9o4zDWieghqQWkah-bP_n8-kM,11977
+markback/llm.py,sha256=ON5_2C6v4KIk7_aIceulfWjEEI6hmallaPlLv-1-s_o,4692
+markback/parser.py,sha256=KHC1QKmN1wSnYgcobC36zXUqL6cdNsZajC6fHlhETZc,19016
+markback/types.py,sha256=t6HdFIWgBTlCfC2KRKKhSO4VBzfxZcP3Uq_zoh-bXZ4,11006
+markback/workflow.py,sha256=zC1RUm1i1wgiciFDqUilJKJ0-bgInvctxhQ0h5WSdoQ,10485
+markback/writer.py,sha256=HY_RYnEk27cIsodo9gGf_MvUb_Bvdmkz05S9kyq6Tdo,8093
+markback-0.1.3.dist-info/METADATA,sha256=ZvzRC2PHMoowUUjoJFzpPzw2425HD7OM-_lr09BOJho,5133
+markback-0.1.3.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+markback-0.1.3.dist-info/entry_points.txt,sha256=Bc9aXvtlPxVPuOJ9BWGngAVrkx5dMvRgujjVzXC-V5U,46
+markback-0.1.3.dist-info/licenses/LICENSE,sha256=lLK1n13C_CXb0M10O-6itEIDY6dsXKutZYQH-09n6s0,1068
+markback-0.1.3.dist-info/RECORD,,

markback-0.1.1.dist-info/RECORD

@@ -1,14 +0,0 @@
-markback/__init__.py,sha256=B0-2dpUu5nkbnUI0hPz-x7PHiOl7M-tiRi6s3UCYJFk,1540
-markback/cli.py,sha256=5wMk1OUG7W_voS9DxeFxRJrBTMabEdOK_s_o3Irxuu0,13639
-markback/config.py,sha256=eTVhb7UwDER9FRYo8QUAvneLHSqXD2ZtLUgtBtnljUs,5455
-markback/linter.py,sha256=JfhQV9R6K6Rm1I0Tu9ugU5d19MegQ9eZHlI_wyjk55k,9653
-markback/llm.py,sha256=ON5_2C6v4KIk7_aIceulfWjEEI6hmallaPlLv-1-s_o,4692
-markback/parser.py,sha256=P7GRjlwhy8j6Tnub7XAqILtZ4pFdkfdHhB-aIjLVRYU,18881
-markback/types.py,sha256=6-aO1tkn9JZ1B47IFi7N9lf5_V8Y0LFrNQMoPgkp8Kc,8707
-markback/workflow.py,sha256=zC1RUm1i1wgiciFDqUilJKJ0-bgInvctxhQ0h5WSdoQ,10485
-markback/writer.py,sha256=3-LeupyuruGv4WZH9pV65hU4YDKuC5HgIIZ8YZ2SZnM,7896
-markback-0.1.1.dist-info/METADATA,sha256=KsRmvJPyZLbvHGcNIeMiemLDTH2z2znLrs9U1SPCUVE,5133
-markback-0.1.1.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-markback-0.1.1.dist-info/entry_points.txt,sha256=Bc9aXvtlPxVPuOJ9BWGngAVrkx5dMvRgujjVzXC-V5U,46
-markback-0.1.1.dist-info/licenses/LICENSE,sha256=lLK1n13C_CXb0M10O-6itEIDY6dsXKutZYQH-09n6s0,1068
-markback-0.1.1.dist-info/RECORD,,