Merge pull request #20 from calebevans/xml

fix(xml): add escaping, root element, and pretty printing

Author: calebevans

docs/architecture.md

@@ -301,33 +301,44 @@ Merged block: lines 10-30 (score=max(0.15, 0.18, 0.12) = 0.18)
 
 ### 6. Output Formatting
 
-**Generates structured XML output with metadata.**
+**Generates pretty-printed, structured XML output with metadata.**
 
 ```xml
-<block lines="581-600" score="0.1746">
-[Sun Dec 04 07:18:00 2005] [error] mod_jk child workerEnv in error state 6
-[Sun Dec 04 07:18:00 2005] [notice] workerEnv.init() ok /etc/httpd/conf/workers2.properties
-[Sun Dec 04 07:18:00 2005] [error] mod_jk child workerEnv in error state 7
-[Sun Dec 04 07:45:45 2005] [error] [client 63.13.186.196] Directory index forbidden by rule: /var/www/html/
-[Sun Dec 04 08:54:17 2005] [error] [client 147.31.138.75] Directory index forbidden by rule: /var/www/html/
-[Sun Dec 04 09:35:12 2005] [error] [client 207.203.80.15] Directory index forbidden by rule: /var/www/html/
-[Sun Dec 04 10:53:30 2005] [error] [client 218.76.139.20] Directory index forbidden by rule: /var/www/html/
-[Sun Dec 04 11:11:07 2005] [error] [client 24.147.151.74] Directory index forbidden by rule: /var/www/html/
-[Sun Dec 04 11:33:18 2005] [error] [client 211.141.93.88] Directory index forbidden by rule: /var/www/html/
-[Sun Dec 04 11:42:43 2005] [error] [client 216.127.124.16] Directory index forbidden by rule: /var/www/html/
-[Sun Dec 04 12:33:13 2005] [error] [client 208.51.151.210] Directory index forbidden by rule: /var/www/html/
-[Sun Dec 04 13:32:32 2005] [error] [client 65.68.235.27] Directory index forbidden by rule: /var/www/html/
-[Sun Dec 04 14:29:00 2005] [error] [client 4.245.93.87] Directory index forbidden by rule: /var/www/html/
-[Sun Dec 04 15:18:36 2005] [error] [client 67.154.58.130] Directory index forbidden by rule: /var/www/html/
-[Sun Dec 04 15:59:01 2005] [error] [client 24.83.37.136] Directory index forbidden by rule: /var/www/html/
-[Sun Dec 04 16:24:03 2005] [notice] jk2_init() Found child 1219 in scoreboard slot 6
-[Sun Dec 04 16:24:05 2005] [error] [client 58.225.62.140] Directory index forbidden by rule: /var/www/html/
-[Sun Dec 04 16:24:06 2005] [notice] workerEnv.init() ok /etc/httpd/conf/workers2.properties
-[Sun Dec 04 16:24:06 2005] [error] mod_jk child workerEnv in error state 6
-[Sun Dec 04 16:31:07 2005] [notice] jk2_init() Found child 1248 in scoreboard slot 7
-</block>
+<?xml version="1.0" encoding="UTF-8"?>
+<anomalies>
+
+  <block lines="581-600" score="0.1746">
+    [Sun Dec 04 07:18:00 2005] [error] mod_jk child workerEnv in error state 6
+    [Sun Dec 04 07:18:00 2005] [notice] workerEnv.init() ok /etc/httpd/conf/workers2.properties
+    [Sun Dec 04 07:18:00 2005] [error] mod_jk child workerEnv in error state 7
+    [Sun Dec 04 07:45:45 2005] [error] [client 63.13.186.196] Directory index forbidden by rule: /var/www/html/
+    [Sun Dec 04 08:54:17 2005] [error] [client 147.31.138.75] Directory index forbidden by rule: /var/www/html/
+    [Sun Dec 04 09:35:12 2005] [error] [client 207.203.80.15] Directory index forbidden by rule: /var/www/html/
+    [Sun Dec 04 10:53:30 2005] [error] [client 218.76.139.20] Directory index forbidden by rule: /var/www/html/
+    [Sun Dec 04 11:11:07 2005] [error] [client 24.147.151.74] Directory index forbidden by rule: /var/www/html/
+    [Sun Dec 04 11:33:18 2005] [error] [client 211.141.93.88] Directory index forbidden by rule: /var/www/html/
+    [Sun Dec 04 11:42:43 2005] [error] [client 216.127.124.16] Directory index forbidden by rule: /var/www/html/
+    [Sun Dec 04 12:33:13 2005] [error] [client 208.51.151.210] Directory index forbidden by rule: /var/www/html/
+    [Sun Dec 04 13:32:32 2005] [error] [client 65.68.235.27] Directory index forbidden by rule: /var/www/html/
+    [Sun Dec 04 14:29:00 2005] [error] [client 4.245.93.87] Directory index forbidden by rule: /var/www/html/
+    [Sun Dec 04 15:18:36 2005] [error] [client 67.154.58.130] Directory index forbidden by rule: /var/www/html/
+    [Sun Dec 04 15:59:01 2005] [error] [client 24.83.37.136] Directory index forbidden by rule: /var/www/html/
+    [Sun Dec 04 16:24:03 2005] [notice] jk2_init() Found child 1219 in scoreboard slot 6
+    [Sun Dec 04 16:24:05 2005] [error] [client 58.225.62.140] Directory index forbidden by rule: /var/www/html/
+    [Sun Dec 04 16:24:06 2005] [notice] workerEnv.init() ok /etc/httpd/conf/workers2.properties
+    [Sun Dec 04 16:24:06 2005] [error] mod_jk child workerEnv in error state 6
+    [Sun Dec 04 16:31:07 2005] [notice] jk2_init() Found child 1248 in scoreboard slot 7
+  </block>
+
+</anomalies>
 ```
 
+**Output structure:**
+- Valid XML with proper declaration and root element
+- Pretty-printed with indentation for readability
+- XML special characters (`&`, `<`, `>`) are automatically escaped
+- Each `<block>` contains metadata and original log content
+
 **Metadata included:**
 - **Line range**: References back to original file
 - **Anomaly score**: Quantifies unusualness

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "cordon"
-version = "0.3.2"
+version = "0.3.3"
 description = "Semantic anomaly detection for system log files"
 readme = "README.md"
 requires-python = ">=3.10"

src/cordon/__init__.py

@@ -2,7 +2,7 @@
 from cordon.core.types import AnalysisResult, MergedBlock, ScoredWindow, TextWindow
 from cordon.pipeline import SemanticLogAnalyzer
 
-__version__ = "0.3.2"
+__version__ = "0.3.3"
 
 __all__ = [
     "SemanticLogAnalyzer",

src/cordon/postprocess/formatter.py

@@ -1,5 +1,6 @@
 from collections.abc import Sequence
 from pathlib import Path
+from xml.sax.saxutils import escape
 
 from cordon.core.types import MergedBlock
 
@@ -26,10 +27,10 @@ def format_blocks(self, merged_blocks: Sequence[MergedBlock], original_file: Pat
             Formatted string with XML tags and original content
         """
         if not merged_blocks:
-            return ""
+            return '<?xml version="1.0" encoding="UTF-8"?>\n<anomalies></anomalies>'
 
         # merged blocks are sorted by start_line from the merger
-        output_parts = []
+        output_parts = ['<?xml version="1.0" encoding="UTF-8"?>', "<anomalies>", ""]
         block_idx = 0
         current_line = 1
 
@@ -51,18 +52,31 @@ def format_blocks(self, merged_blocks: Sequence[MergedBlock], original_file: Pat
                         content_lines.append(next_line)
                         current_line += 1
 
-                    # format the block
+                    # format the block with indentation
                     tag = (
-                        f'<block lines="{block.start_line}-{block.end_line}" '
+                        f'  <block lines="{block.start_line}-{block.end_line}" '
                         f'score="{block.max_score:.4f}">'
                     )
                     content = "".join(content_lines)
-                    output_parts.append(f"{tag}\n{content}</block>")
+                    # Escape XML special characters to ensure valid XML output
+                    escaped_content = escape(content)
+
+                    # Indent each line of content for pretty printing
+                    # Preserve whitespace-only lines from original content
+                    indented_content = "\n".join(
+                        "    " + line if line else line for line in escaped_content.splitlines()
+                    )
+
+                    output_parts.append(f"{tag}\n{indented_content}\n  </block>")
+                    output_parts.append("")  # blank line between blocks
 
                     # move to next block
                     block_idx += 1
 
                 current_line += 1
 
-        # join blocks with double newline separator
-        return "\n\n".join(output_parts)
+        # close the root element
+        output_parts.append("</anomalies>")
+
+        # join with newlines
+        return "\n".join(output_parts)

tests/test_integration.py

@@ -56,7 +56,9 @@ def test_analyze_empty_log(self) -> None:
             assert result.total_windows == 0
             assert result.significant_windows == 0
             assert result.merged_blocks == 0
-            assert result.output == ""
+            assert (
+                result.output == '<?xml version="1.0" encoding="UTF-8"?>\n<anomalies></anomalies>'
+            )
         finally:
             temp_path.unlink()
 

tests/test_postprocess.py

@@ -136,6 +136,9 @@ def test_format_single_block(self) -> None:
             formatter = OutputFormatter()
             output = formatter.format_blocks(blocks, temp_path)
 
+            assert '<?xml version="1.0" encoding="UTF-8"?>' in output
+            assert "<anomalies>" in output
+            assert "</anomalies>" in output
             assert '<block lines="1-2" score="0.8000">' in output
             assert "line 1\n" in output
             assert "line 2\n" in output
@@ -161,6 +164,9 @@ def test_format_multiple_blocks(self) -> None:
             formatter = OutputFormatter()
             output = formatter.format_blocks(blocks, temp_path)
 
+            assert '<?xml version="1.0" encoding="UTF-8"?>' in output
+            assert "<anomalies>" in output
+            assert "</anomalies>" in output
             assert '<block lines="1-2" score="0.8000">' in output
             assert '<block lines="5-7" score="0.9000">' in output
             assert output.count("</block>") == 2
@@ -181,6 +187,40 @@ def test_format_empty_blocks(self) -> None:
             formatter = OutputFormatter()
             output = formatter.format_blocks(blocks, temp_path)
 
-            assert output == ""
+            assert output == '<?xml version="1.0" encoding="UTF-8"?>\n<anomalies></anomalies>'
+        finally:
+            temp_path.unlink()
+
+    def test_format_escapes_xml_special_chars(self) -> None:
+        """Test that XML special characters are properly escaped."""
+        with NamedTemporaryFile(mode="w", delete=False, suffix=".log") as f:
+            f.write("command: test |& tee file.txt\n")
+            f.write("error: x < y && z > 10\n")
+            f.write("message: \"quoted\" & 'single'\n")
+            temp_path = Path(f.name)
+
+        try:
+            from cordon.core.types import MergedBlock
+
+            blocks = [MergedBlock(start_line=1, end_line=3, original_windows=(0,), max_score=0.8)]
+
+            formatter = OutputFormatter()
+            output = formatter.format_blocks(blocks, temp_path)
+
+            # Verify XML structure
+            assert '<?xml version="1.0" encoding="UTF-8"?>' in output
+            assert "<anomalies>" in output
+            assert "</anomalies>" in output
+            # Verify XML special characters are escaped (& < > must be escaped in text content)
+            assert "&amp;" in output
+            assert "&lt;" in output
+            assert "&gt;" in output
+            # Verify the content is properly escaped
+            assert "command: test |&amp; tee file.txt" in output
+            assert "error: x &lt; y &amp;&amp; z &gt; 10" in output
+            # Verify raw special characters are not present where they should be escaped
+            assert "|& tee" not in output  # & should be escaped
+            assert "x < y" not in output  # < should be escaped
+            assert "z > 10" not in output  # > should be escaped
         finally:
             temp_path.unlink()