markback 0.1.0__py3-none-any.whl → 0.1.2__py3-none-any.whl

markback/linter.py

@@ -110,6 +110,69 @@ def lint_source_exists(
     return diagnostics
 
 
+def lint_prior_exists(
+    record: Record,
+    base_path: Optional[Path],
+    record_idx: int,
+) -> list[Diagnostic]:
+    """Check if @prior file exists."""
+    diagnostics: list[Diagnostic] = []
+
+    if record.prior and not record.prior.is_uri:
+        try:
+            resolved = record.prior.resolve(base_path)
+            if not resolved.exists():
+                diagnostics.append(Diagnostic(
+                    file=record._source_file,
+                    line=record._start_line,
+                    column=None,
+                    severity=Severity.WARNING,
+                    code=WarningCode.W009,
+                    message=f"@prior file not found: {record.prior}",
+                    record_index=record_idx,
+                ))
+        except ValueError:
+            pass  # URI that can't be resolved to path
+
+    return diagnostics
+
+
+def lint_line_range(
+    record: Record,
+    record_idx: int,
+) -> list[Diagnostic]:
+    """Check if line ranges are valid (end >= start)."""
+    diagnostics: list[Diagnostic] = []
+
+    # Check @source line range
+    if record.source and record.source.start_line is not None:
+        if record.source.end_line is not None and record.source.end_line < record.source.start_line:
+            diagnostics.append(Diagnostic(
+                file=record._source_file,
+                line=record._start_line,
+                column=None,
+                severity=Severity.ERROR,
+                code=ErrorCode.E011,
+                message=f"Invalid line range in @source: end line {record.source.end_line} is less than start line {record.source.start_line}",
+                record_index=record_idx,
+            ))
+
+    # Check @prior line range
+    if record.prior and record.prior.start_line is not None:
+        if record.prior.end_line is not None and record.prior.end_line < record.prior.start_line:
+            diagnostics.append(Diagnostic(
+                file=record._source_file,
+                line=record._start_line,
+                column=None,
+                severity=Severity.ERROR,
+                code=ErrorCode.E011,
+                message=f"Invalid line range in @prior: end line {record.prior.end_line} is less than start line {record.prior.start_line}",
+                record_index=record_idx,
+            ))
+
+    return diagnostics
+
+
 def lint_canonical_format(
     records: list[Record],
     original_text: str,
@@ -173,10 +236,14 @@ def lint_string(
                 idx,
             ))
 
-        # Check source file existence
+        # Check source and prior file existence
         if check_sources:
             base_path = source_file.parent if source_file else None
             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:

markback/parser.py

@@ -17,7 +17,7 @@ from .types import (
 
 
 # Known header keywords
-KNOWN_HEADERS = {"uri", "source"}
+KNOWN_HEADERS = {"uri", "source", "prior"}
 
 # Patterns
 HEADER_PATTERN = re.compile(r"^@([a-z]+)\s+(.+)$")
@@ -147,6 +147,8 @@ def parse_string(
         uri = current_headers.get("uri") or pending_uri
         source_str = current_headers.get("source")
         source = SourceRef(source_str) if source_str else None
+        prior_str = current_headers.get("prior")
+        prior = SourceRef(prior_str) if prior_str else None
 
         content = None
         if current_content_lines:
@@ -163,6 +165,7 @@ def parse_string(
             feedback=feedback,
             uri=uri,
             source=source,
+            prior=prior,
             content=content,
             _source_file=source_file,
             _start_line=current_start_line,
@@ -239,13 +242,16 @@ def parse_string(
                     line_num,
                 )
 
-            # Use any pending @uri from previous line
+            # Use any pending @uri from previous line and @prior if present
             uri = pending_uri or current_headers.get("uri")
+            prior_str = current_headers.get("prior")
+            prior = SourceRef(prior_str) if prior_str else None
 
             record = Record(
                 feedback=feedback or "",
                 uri=uri,
                 source=source,
+                prior=prior,
                 content=None,
                 _source_file=source_file,
                 _start_line=current_start_line,

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):
@@ -37,6 +39,7 @@ class WarningCode(Enum):
     W006 = "W006"  # Missing @uri (record has no identifier)
     W007 = "W007"  # Paired feedback file not found
     W008 = "W008"  # Non-canonical formatting detected
+    W009 = "W009"  # @prior file not found
 
 
 @dataclass
@@ -75,29 +78,67 @@ class Diagnostic:
         }
 
 
+# Regex to parse line range from a path: path:start or path:start-end
+_LINE_RANGE_PATTERN = re.compile(r'^(.+?):(\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
+    _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 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.end_line = int(match.group(3))
+            else:
+                # Single line reference: start and end are the same
+                self.end_line = self.start_line
+        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 range string, or None if no range."""
+        if self.start_line is None:
+            return None
+        if self.start_line == self.end_line:
+            return f":{self.start_line}"
+        return f":{self.start_line}-{self.end_line}"
+
     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 +163,7 @@ class Record:
     feedback: str
     uri: Optional[str] = None
     source: Optional[SourceRef] = None
+    prior: Optional[SourceRef] = None
     content: Optional[str] = None
     metadata: dict = field(default_factory=dict)
 
@@ -154,6 +196,7 @@ class Record:
         return {
             "uri": self.uri,
             "source": str(self.source) if self.source else None,
+            "prior": str(self.prior) if self.prior else None,
             "content": self.content,
             "feedback": self.feedback,
             "metadata": self.metadata,

markback/writer.py

@@ -38,15 +38,19 @@ def write_record_canonical(
     )
 
     if use_compact:
-        # Compact format: @uri on its own line (if present), then @source ... <<<
+        # Compact format: @uri on its own line (if present), then @prior, then @source ... <<<
         if record.uri:
             lines.append(f"@uri {record.uri}")
+        if record.prior:
+            lines.append(f"@prior {record.prior}")
         lines.append(f"@source {record.source} <<< {record.feedback}")
     else:
         # Full format
-        # Headers: @uri first, then @source
+        # Headers: @uri first, then @prior, then @source
         if record.uri:
             lines.append(f"@uri {record.uri}")
+        if record.prior:
+            lines.append(f"@prior {record.prior}")
         if record.source:
             lines.append(f"@source {record.source}")
 
@@ -147,6 +151,9 @@ def write_label_file(record: Record) -> str:
 
     if record.uri:
         lines.append(f"@uri {record.uri}")
+    
+    if record.prior:
+        lines.append(f"@prior {record.prior}")
 
     lines.append(f"<<< {record.feedback}")
 

{markback-0.1.0.dist-info → markback-0.1.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: markback
-Version: 0.1.0
+Version: 0.1.2
 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
@@ -196,6 +196,16 @@ Second content.
 @source ./images/003.jpg <<< approved; scene=mountain
 ```
 
+### With Prior Reference
+
+Use `@prior` to reference an item that precedes the source (e.g., a prompt that generated an image):
+
+```
+@uri local:generated-001
+@prior ./prompts/sunset-prompt.txt
+@source ./images/generated-sunset.jpg <<< accurate; matches prompt well
+```
+
 ### Paired Files
 
 **content.txt:**

markback-0.1.2.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=IctgPEFNfGDo5DcELdo0Ni3d7Dp0bIWtlDw61ccWDOQ,11210
+markback/llm.py,sha256=ON5_2C6v4KIk7_aIceulfWjEEI6hmallaPlLv-1-s_o,4692
+markback/parser.py,sha256=P7GRjlwhy8j6Tnub7XAqILtZ4pFdkfdHhB-aIjLVRYU,18881
+markback/types.py,sha256=tFunBAoqUEVf9mi_4N1QwWmOsKt0nocZK7M7K_rybWg,10097
+markback/workflow.py,sha256=zC1RUm1i1wgiciFDqUilJKJ0-bgInvctxhQ0h5WSdoQ,10485
+markback/writer.py,sha256=3-LeupyuruGv4WZH9pV65hU4YDKuC5HgIIZ8YZ2SZnM,7896
+markback-0.1.2.dist-info/METADATA,sha256=d_xMmpicyEYeakJ4hA8SsrlGgj5Qxpd6fMv7tKf-eaI,5133
+markback-0.1.2.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+markback-0.1.2.dist-info/entry_points.txt,sha256=Bc9aXvtlPxVPuOJ9BWGngAVrkx5dMvRgujjVzXC-V5U,46
+markback-0.1.2.dist-info/licenses/LICENSE,sha256=lLK1n13C_CXb0M10O-6itEIDY6dsXKutZYQH-09n6s0,1068
+markback-0.1.2.dist-info/RECORD,,

markback-0.1.0.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=6jrfngF4PiYFQlDddm09OEmVSSGwacE5YFxMub5mqlA,8707
-markback/llm.py,sha256=ON5_2C6v4KIk7_aIceulfWjEEI6hmallaPlLv-1-s_o,4692
-markback/parser.py,sha256=5CrLeOWGuiE0_BOK9dJUnLLrJ72KTmucyOQEzR1nDh4,18570
-markback/types.py,sha256=rRy41h1ZYYP9lo_FhvP5X5-OlwEM7vzHCw--Sq5L2LA,8564
-markback/workflow.py,sha256=zC1RUm1i1wgiciFDqUilJKJ0-bgInvctxhQ0h5WSdoQ,10485
-markback/writer.py,sha256=v5KT2o2Ma2I9I4U-r06PgzKyqwQFSsx49Ri5qIsovhY,7645
-markback-0.1.0.dist-info/METADATA,sha256=aqRMZiWqsEExkqi_dwSyWtcFb3uhOx2Ol6HbNBU7Ggw,4864
-markback-0.1.0.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-markback-0.1.0.dist-info/entry_points.txt,sha256=Bc9aXvtlPxVPuOJ9BWGngAVrkx5dMvRgujjVzXC-V5U,46
-markback-0.1.0.dist-info/licenses/LICENSE,sha256=lLK1n13C_CXb0M10O-6itEIDY6dsXKutZYQH-09n6s0,1068
-markback-0.1.0.dist-info/RECORD,,