feat: Add element content capture (Issue #159)

.gitignore

@@ -37,3 +37,9 @@ build/
 # Serena/Vibe working directories
 .serena/
 .vibe/
+
+# Playwright MCP screenshots
+.playwright-mcp/
+
+# Test reports
+report.html

src/dacli/api/content.py

@@ -178,6 +178,7 @@ def get_elements(
                     start_line=elem.source_location.line,
                     end_line=elem.source_location.end_line or elem.source_location.line,
                 ),
+                attributes=elem.attributes,  # Issue #159: Include element attributes
             )
         )
 

src/dacli/api/models.py

@@ -4,7 +4,7 @@
 and Content Access API as specified in 02_api_specification.adoc.
 """
 
-from typing import Literal
+from typing import Any, Literal
 
 from pydantic import BaseModel, Field
 
@@ -123,6 +123,10 @@ class ElementItem(BaseModel):
     path: str = Field(description="Section path containing this element")
     index: int = Field(description="Index of element within its section")
     location: ElementLocation
+    attributes: dict[str, Any] = Field(
+        default_factory=dict,
+        description="Element-specific attributes and content (Issue #159)",
+    )
     # Note: preview field removed in Issue #142 as redundant
 
 

src/dacli/asciidoc_parser.py

@@ -667,6 +667,13 @@ def _parse_elements(
         current_list_element: Element | None = None  # Track list for end_line (#136)
         # Track ALL open blocks for end_line (Issue #157: use stack instead of single element)
         open_blocks: list[Element] = []
+        # Content tracking for Issue #159
+        code_block_content: list[str] = []
+        plantuml_content: list[str] = []
+        mermaid_content: list[str] = []
+        ditaa_content: list[str] = []
+        table_content: list[str] = []
+        list_content: list[str] = []
 
         for line_text, source_file, line_num, resolved_from in lines:
             # Track current section for parent_section
@@ -723,6 +730,7 @@ def _sub_attr(match: re.Match) -> str:
                     if pending_plantuml_info is not None:
                         # Start of plantuml block
                         in_plantuml_block = True
+                        plantuml_content = []  # Initialize content tracking (Issue #159)
                         name, fmt = pending_plantuml_info
                         element = self._create_diagram_element(
                             "plantuml", name, fmt, source_file, line_num,
@@ -734,6 +742,7 @@ def _sub_attr(match: re.Match) -> str:
                     elif pending_mermaid_info is not None:
                         # Start of mermaid block
                         in_mermaid_block = True
+                        mermaid_content = []  # Initialize content tracking (Issue #159)
                         name, fmt = pending_mermaid_info
                         element = self._create_diagram_element(
                             "mermaid", name, fmt, source_file, line_num,
@@ -745,6 +754,7 @@ def _sub_attr(match: re.Match) -> str:
                     elif pending_ditaa_info is not None:
                         # Start of ditaa block
                         in_ditaa_block = True
+                        ditaa_content = []  # Initialize content tracking (Issue #159)
                         name, fmt = pending_ditaa_info
                         element = self._create_diagram_element(
                             "ditaa", name, fmt, source_file, line_num,
@@ -756,6 +766,7 @@ def _sub_attr(match: re.Match) -> str:
                     elif pending_code_language is not None:
                         # Start of code block
                         in_code_block = True
+                        code_block_content = []  # Initialize content tracking (Issue #159)
                         source_location = SourceLocation(
                             file=source_file,
                             line=line_num,
@@ -771,19 +782,27 @@ def _sub_attr(match: re.Match) -> str:
                         open_blocks.append(element)
                     pending_code_language = None
                 elif in_code_block:
-                    # End of code block
+                    # End of code block - save content (Issue #159)
+                    if open_blocks:
+                        open_blocks[-1].attributes["content"] = "\n".join(code_block_content)
                     in_code_block = False
                     self._close_open_block(open_blocks, line_num)
                 elif in_plantuml_block:
-                    # End of plantuml block
+                    # End of plantuml block - save content (Issue #159)
+                    if open_blocks:
+                        open_blocks[-1].attributes["content"] = "\n".join(plantuml_content)
                     in_plantuml_block = False
                     self._close_open_block(open_blocks, line_num)
                 elif in_mermaid_block:
-                    # End of mermaid block
+                    # End of mermaid block - save content (Issue #159)
+                    if open_blocks:
+                        open_blocks[-1].attributes["content"] = "\n".join(mermaid_content)
                     in_mermaid_block = False
                     self._close_open_block(open_blocks, line_num)
                 elif in_ditaa_block:
-                    # End of ditaa block
+                    # End of ditaa block - save content (Issue #159)
+                    if open_blocks:
+                        open_blocks[-1].attributes["content"] = "\n".join(ditaa_content)
                     in_ditaa_block = False
                     self._close_open_block(open_blocks, line_num)
                 continue
@@ -793,6 +812,7 @@ def _sub_attr(match: re.Match) -> str:
                 if not in_table:
                     # Start of table
                     in_table = True
+                    table_content = []  # Initialize content tracking (Issue #159)
                     source_location = SourceLocation(
                         file=source_file,
                         line=line_num,
@@ -807,7 +827,9 @@ def _sub_attr(match: re.Match) -> str:
                     elements.append(element)
                     open_blocks.append(element)
                 else:
-                    # End of table
+                    # End of table - save content (Issue #159)
+                    if open_blocks:
+                        open_blocks[-1].attributes["content"] = "\n".join(table_content)
                     in_table = False
                     self._close_open_block(open_blocks, line_num)
                 continue
@@ -852,36 +874,52 @@ def _sub_attr(match: re.Match) -> str:
                         parent_section=current_section_path,
                     )
                 )
+                # Save list content before reset (Issue #159)
+                if current_list_element is not None and list_content:
+                    current_list_element.attributes["content"] = "\n".join(list_content)
                 current_list_type = None  # Reset list tracking
+                current_list_element = None
                 continue
 
             # Detect lists (unordered, ordered, description)
             # Check for unordered list (* item)
             if UNORDERED_LIST_PATTERN.match(line_text):
                 if current_list_type != "unordered":
+                    # Save previous list content if any (Issue #159)
+                    if current_list_element is not None and list_content:
+                        current_list_element.attributes["content"] = "\n".join(list_content)
                     # Start of a new unordered list
                     current_list_type = "unordered"
+                    list_content = []  # Initialize content tracking (Issue #159)
                     current_list_element = self._create_list_element(
                         "unordered", source_file, line_num,
                         resolved_from, current_section_path,
                     )
                     elements.append(current_list_element)
-                elif current_list_element is not None:
+                # Collect list item content (Issue #159)
+                list_content.append(line_text)
+                if current_list_element is not None:
                     # Continue list - update end_line (Issue #136)
                     current_list_element.source_location.end_line = line_num
                 continue
 
             # Check for ordered list (. item)
             if ORDERED_LIST_PATTERN.match(line_text):
                 if current_list_type != "ordered":
+                    # Save previous list content if any (Issue #159)
+                    if current_list_element is not None and list_content:
+                        current_list_element.attributes["content"] = "\n".join(list_content)
                     # Start of a new ordered list
                     current_list_type = "ordered"
+                    list_content = []  # Initialize content tracking (Issue #159)
                     current_list_element = self._create_list_element(
                         "ordered", source_file, line_num,
                         resolved_from, current_section_path,
                     )
                     elements.append(current_list_element)
-                elif current_list_element is not None:
+                # Collect list item content (Issue #159)
+                list_content.append(line_text)
+                if current_list_element is not None:
                     # Continue list - update end_line (Issue #136)
                     current_list_element.source_location.end_line = line_num
                 continue
@@ -903,9 +941,24 @@ def _sub_attr(match: re.Match) -> str:
 
             # If line is not a list item, reset list tracking
             if line_text.strip():
+                # Save list content before reset (Issue #159)
+                if current_list_element is not None and list_content:
+                    current_list_element.attributes["content"] = "\n".join(list_content)
                 current_list_type = None
                 current_list_element = None
 
+            # Collect content for open blocks (Issue #159)
+            if in_code_block:
+                code_block_content.append(line_text)
+            elif in_plantuml_block:
+                plantuml_content.append(line_text)
+            elif in_mermaid_block:
+                mermaid_content.append(line_text)
+            elif in_ditaa_block:
+                ditaa_content.append(line_text)
+            elif in_table:
+                table_content.append(line_text)
+
         # Handle ALL unclosed blocks - set end_line to last line of their source file
         # Issue #146: unclosed code blocks should have proper end_line
         # Issue #157: ALL unclosed blocks should be detected, not just the last one
@@ -938,6 +991,10 @@ def _sub_attr(match: re.Match) -> str:
                 message=warning_msg,
             ))
 
+        # Save list content if list is still open at end of file (Issue #159)
+        if current_list_element is not None and list_content:
+            current_list_element.attributes["content"] = "\n".join(list_content)
+
         return elements, warnings
 
     def _find_section_path(self, sections: list[Section], title: str) -> str:

src/dacli/cli.py

@@ -480,44 +480,63 @@ def search(ctx: CliContext, query: str, scope: str | None, max_results: int):
 
 @cli.command(epilog="""
 Examples:
-  dacli elements                         # All elements
-  dacli elements --type code             # Only code blocks
-  dacli elements --type table            # Only tables
-  dacli elements api                     # Elements in 'api' section
-  dacli elements api --recursive         # Elements in 'api' and all subsections
-  dacli --format json el --type image    # JSON output using alias
+  dacli elements                             # All elements (metadata only)
+  dacli elements --type code                 # Only code blocks
+  dacli elements --include-content           # Include element content
+  dacli elements --include-content --content-limit 10  # First 10 lines only
+  dacli elements api --recursive             # Elements in 'api' and subsections
+  dacli --format json el --type image        # JSON output using alias
 """)
 @click.argument("section_path", required=False, default=None)
 @click.option("--type", "element_type", default=None,
               help="Element type: code, table, image, diagram, list")
 @click.option("--recursive", is_flag=True, default=False,
               help="Include elements from child sections")
+@click.option("--include-content", is_flag=True, default=False,
+              help="Include element content (Issue #159)")
+@click.option("--content-limit", type=int, default=None,
+              help="Limit content to first N lines (requires --include-content)")
 @pass_context
 def elements(ctx: CliContext, section_path: str | None, element_type: str | None,
-             recursive: bool):
+             recursive: bool, include_content: bool, content_limit: int | None):
     """Get elements (code blocks, tables, images) from documentation."""
     elems = ctx.index.get_elements(
         element_type=element_type,
         section_path=section_path,
         recursive=recursive,
     )
 
-    # Note: preview field removed in Issue #142 as redundant
-    # The type field is sufficient to identify element kind
+    # Build element dicts with optional content (Issue #159)
+    element_dicts = []
+    for e in elems:
+        elem_dict = {
+            "type": e.type,
+            "parent_section": e.parent_section,
+            "location": {
+                "file": str(e.source_location.file),
+                "start_line": e.source_location.line,
+                "end_line": e.source_location.end_line,
+            },
+        }
+
+        # Include attributes if requested (Issue #159)
+        if include_content:
+            attributes = dict(e.attributes)  # Copy attributes
+
+            # Apply content limit if specified
+            if content_limit is not None and "content" in attributes:
+                content = attributes["content"]
+                lines = content.split("\n")
+                if len(lines) > content_limit:
+                    attributes["content"] = "\n".join(lines[:content_limit])
+
+            elem_dict["attributes"] = attributes
+
+        element_dicts.append(elem_dict)
+
     result = {
-        "elements": [
-            {
-                "type": e.type,
-                "parent_section": e.parent_section,
-                "location": {
-                    "file": str(e.source_location.file),
-                    "start_line": e.source_location.line,
-                    "end_line": e.source_location.end_line,
-                },
-            }
-            for e in elems
-        ],
-        "count": len(elems),
+        "elements": element_dicts,
+        "count": len(element_dicts),
     }
     click.echo(format_output(ctx, result))