gateway/modules/services/serviceGeneration/renderers/rendererCsv.py

258 lines
9.6 KiB
Python

"""
CSV renderer for report generation.
"""
from .rendererBaseTemplate import BaseRenderer
from typing import Dict, Any, Tuple, List
class RendererCsv(BaseRenderer):
"""Renders content to CSV format with format-specific extraction."""
@classmethod
def getSupportedFormats(cls) -> List[str]:
"""Return supported CSV formats."""
return ['csv']
@classmethod
def getFormatAliases(cls) -> List[str]:
"""Return format aliases."""
return ['spreadsheet', 'table']
@classmethod
def getPriority(cls) -> int:
"""Return priority for CSV renderer."""
return 70
async def render(self, extractedContent: Dict[str, Any], title: str, userPrompt: str = None, aiService=None) -> Tuple[str, str]:
"""Render extracted JSON content to CSV format."""
try:
# Generate CSV directly from JSON (no styling needed for CSV)
csvContent = await self._generateCsvFromJson(extractedContent, title)
return csvContent, "text/csv"
except Exception as e:
self.logger.error(f"Error rendering CSV: {str(e)}")
# Return minimal CSV fallback
return f"Title,Content\n{title},Error rendering report: {str(e)}", "text/csv"
async def _generateCsvFromJson(self, jsonContent: Dict[str, Any], title: str) -> str:
"""Generate CSV content from structured JSON document."""
try:
# Validate JSON structure
if not isinstance(jsonContent, dict):
raise ValueError("JSON content must be a dictionary")
if "sections" not in jsonContent:
raise ValueError("JSON content must contain 'sections' field")
# Use title from JSON metadata if available, otherwise use provided title
documentTitle = jsonContent.get("metadata", {}).get("title", title)
# Generate CSV content
csvRows = []
# Add title row
if documentTitle:
csvRows.append([documentTitle])
csvRows.append([]) # Empty row
# Process each section in order
sections = jsonContent.get("sections", [])
for section in sections:
sectionCsv = self._renderJsonSectionToCsv(section)
if sectionCsv:
csvRows.extend(sectionCsv)
csvRows.append([]) # Empty row between sections
# Convert to CSV string
csvContent = self._convertRowsToCsv(csvRows)
return csvContent
except Exception as e:
self.logger.error(f"Error generating CSV from JSON: {str(e)}")
raise Exception(f"CSV generation failed: {str(e)}")
def _renderJsonSectionToCsv(self, section: Dict[str, Any]) -> List[List[str]]:
"""Render a single JSON section to CSV rows."""
try:
sectionType = section.get("content_type", "paragraph")
elements = section.get("elements", [])
csvRows = []
# Add section title if available
sectionTitle = section.get("title")
if sectionTitle:
csvRows.append([f"# {sectionTitle}"])
# Process each element in the section
for element in elements:
if sectionType == "table":
csvRows.extend(self._renderJsonTableToCsv(element))
elif sectionType == "list":
csvRows.extend(self._renderJsonListToCsv(element))
elif sectionType == "heading":
csvRows.extend(self._renderJsonHeadingToCsv(element))
elif sectionType == "paragraph":
csvRows.extend(self._renderJsonParagraphToCsv(element))
elif sectionType == "code":
csvRows.extend(self._renderJsonCodeToCsv(element))
else:
# Fallback to paragraph for unknown types
csvRows.extend(self._renderJsonParagraphToCsv(element))
return csvRows
except Exception as e:
self.logger.warning(f"Error rendering section {section.get('id', 'unknown')}: {str(e)}")
return [["[Error rendering section]"]]
def _renderJsonTableToCsv(self, tableData: Dict[str, Any]) -> List[List[str]]:
"""Render a JSON table to CSV rows."""
try:
headers = tableData.get("headers", [])
rows = tableData.get("rows", [])
csvRows = []
if headers:
csvRows.append(headers)
if rows:
csvRows.extend(rows)
return csvRows
except Exception as e:
self.logger.warning(f"Error rendering table: {str(e)}")
return [["[Error rendering table]"]]
def _renderJsonListToCsv(self, listData: Dict[str, Any]) -> List[List[str]]:
"""Render a JSON list to CSV rows."""
try:
items = listData.get("items", [])
csvRows = []
for item in items:
if isinstance(item, dict):
text = item.get("text", "")
subitems = item.get("subitems", [])
csvRows.append([text])
# Add subitems as indented rows
for subitem in subitems:
if isinstance(subitem, dict):
csvRows.append([f" - {subitem.get('text', '')}"])
else:
csvRows.append([f" - {subitem}"])
else:
csvRows.append([str(item)])
return csvRows
except Exception as e:
self.logger.warning(f"Error rendering list: {str(e)}")
return [["[Error rendering list]"]]
def _renderJsonHeadingToCsv(self, headingData: Dict[str, Any]) -> List[List[str]]:
"""Render a JSON heading to CSV rows."""
try:
text = headingData.get("text", "")
level = headingData.get("level", 1)
if text:
# Use # symbols for heading levels
headingText = f"{'#' * level} {text}"
return [[headingText]]
return []
except Exception as e:
self.logger.warning(f"Error rendering heading: {str(e)}")
return [["[Error rendering heading]"]]
def _renderJsonParagraphToCsv(self, paragraphData: Dict[str, Any]) -> List[List[str]]:
"""Render a JSON paragraph to CSV rows."""
try:
text = paragraphData.get("text", "")
if text:
# Split long paragraphs into multiple rows if needed
if len(text) > 100:
words = text.split()
rows = []
currentRow = []
currentLength = 0
for word in words:
if currentLength + len(word) > 100 and currentRow:
rows.append([" ".join(currentRow)])
currentRow = [word]
currentLength = len(word)
else:
currentRow.append(word)
currentLength += len(word) + 1
if currentRow:
rows.append([" ".join(currentRow)])
return rows
else:
return [[text]]
return []
except Exception as e:
self.logger.warning(f"Error rendering paragraph: {str(e)}")
return [["[Error rendering paragraph]"]]
def _renderJsonCodeToCsv(self, codeData: Dict[str, Any]) -> List[List[str]]:
"""Render a JSON code block to CSV rows."""
try:
code = codeData.get("code", "")
language = codeData.get("language", "")
csvRows = []
if language:
csvRows.append([f"Code ({language}):"])
if code:
# Split code into lines
codeLines = code.split('\n')
for line in codeLines:
csvRows.append([f" {line}"])
return csvRows
except Exception as e:
self.logger.warning(f"Error rendering code block: {str(e)}")
return [["[Error rendering code block]"]]
def _convertRowsToCsv(self, rows: List[List[str]]) -> str:
"""Convert rows to CSV string."""
import csv
import io
output = io.StringIO()
writer = csv.writer(output)
for row in rows:
if row: # Only write non-empty rows
writer.writerow(row)
return output.getvalue()
def _cleanCsvContent(self, content: str, title: str) -> str:
"""Clean and validate CSV content from AI."""
content = content.strip()
# Remove markdown code blocks if present
if content.startswith("```") and content.endswith("```"):
lines = content.split('\n')
if len(lines) > 2:
content = '\n'.join(lines[1:-1]).strip()
return content