edsl 0.1.39.dev1__py3-none-any.whl → 0.1.39.dev2__py3-none-any.whl

edsl/results/DatasetTree.py

@@ -1,8 +1,4 @@
 from typing import Dict, List, Any, Optional, List
-from docx import Document
-from docx.shared import Inches, Pt
-from docx.enum.text import WD_ALIGN_PARAGRAPH
-from docx.enum.style import WD_STYLE_TYPE
 
 
 def is_hashable(v):
@@ -98,6 +94,11 @@ class Tree:
         if filename is None:
             filename = "tree_structure.docx"
 
+        from docx import Document
+        from docx.shared import Inches, Pt
+        from docx.enum.text import WD_ALIGN_PARAGRAPH
+        from docx.enum.style import WD_STYLE_TYPE
+
         doc = Document()
 
         # Create styles for headings
@@ -115,10 +116,29 @@ class Tree:
         body_style.font.size = Pt(11)
 
         self._add_to_docx(doc, self.root, 0)
-        doc.save(filename)
-        from edsl.utilities.utilities import file_notice
-
-        file_notice(filename)
+        import base64
+        from io import BytesIO
+        import base64
+
+        # Save document to bytes buffer
+        doc_buffer = BytesIO()
+        doc.save(doc_buffer)
+        doc_buffer.seek(0)
+
+        base64_string = base64.b64encode(doc_buffer.getvalue()).decode("utf-8")
+        from edsl.scenarios.FileStore import FileStore
+
+        # Create and return FileStore instance
+        return FileStore(
+            path="tree_structure.docx",  # Default name
+            mime_type="application/vnd.openxmlformats-officedocument.wordprocessingml.document",
+            binary=True,
+            suffix="docx",
+            base64_string=base64_string,
+        )
+        # doc.save(filename)
+        # from edsl.utilities.utilities import file_notice
+        # file_notice(filename)
 
     def _repr_html_(self):
         """Returns an interactive HTML representation of the tree with collapsible sections."""

edsl/results/MarkdownToDocx.py

@@ -0,0 +1,122 @@
+from typing import Optional
+import subprocess
+import os
+from pathlib import Path
+import tempfile
+
+
+class MarkdownToDocx:
+    def __init__(self, markdown_content: str, filename: Optional[str] = None):
+        """
+        Initialize the converter with markdown content.
+
+        Args:
+            markdown_content (str): The markdown content to be converted
+        """
+        self.markdown_content = markdown_content
+        self.filename = filename
+        self._check_pandoc()
+
+    def _check_pandoc(self):
+        """Check if pandoc is installed and accessible."""
+        try:
+            subprocess.run(["pandoc", "--version"], capture_output=True, check=True)
+        except (subprocess.CalledProcessError, FileNotFoundError):
+            raise RuntimeError(
+                "Pandoc is not installed or not found in PATH. "
+                "Please install pandoc before using this converter."
+            )
+
+    def convert(self, output_path: str, **options) -> bool:
+        """
+        Convert the markdown content to DOCX.
+
+        Args:
+            output_path (str): Path where the DOCX should be saved
+            **options: Additional conversion options
+                reference_doc (str): Path to reference docx for styling
+                toc (bool): Include table of contents (default: False)
+                number_sections (bool): Number sections (default: False)
+                highlight_style (str): Code highlighting style (default: "tango")
+
+        Returns:
+            bool: True if conversion was successful, False otherwise
+        """
+        # Ensure output directory exists
+        output_path = Path(output_path)
+        output_path.parent.mkdir(parents=True, exist_ok=True)
+
+        # Build pandoc command
+        cmd = ["pandoc", "-f", "markdown", "-t", "docx", "-o", str(output_path)]
+
+        # Add reference doc if provided
+        if "reference_doc" in options:
+            ref_doc = Path(options["reference_doc"])
+            if ref_doc.exists():
+                cmd.extend(["--reference-doc", str(ref_doc)])
+            else:
+                print(f"Warning: Reference document {ref_doc} not found")
+
+        # Add optional parameters
+        if options.get("toc", False):
+            cmd.append("--toc")
+
+        if options.get("number_sections", False):
+            cmd.append("--number-sections")
+
+        if "highlight_style" in options:
+            cmd.extend(["--highlight-style", options["highlight_style"]])
+
+        try:
+            # Run pandoc command
+            result = subprocess.run(
+                cmd,
+                input=self.markdown_content,
+                text=True,
+                capture_output=True,
+                check=True,
+            )
+            return True
+        except subprocess.CalledProcessError as e:
+            print(f"Error converting markdown to DOCX: {e.stderr}")
+            return False
+
+    def preview(self) -> str:
+        """
+        Generate a temporary DOCX and return its path.
+
+        Returns:
+            str: Path to the temporary DOCX file
+        """
+        temp_dir = tempfile.mkdtemp()
+        if self.filename:
+            temp_docx = os.path.join(temp_dir, self.filename)
+        else:
+            temp_docx = os.path.join(temp_dir, "preview.docx")
+
+        if self.convert(temp_docx):
+            from edsl.scenarios.FileStore import FileStore
+
+            return FileStore(path=temp_docx)
+
+        return None
+
+    def create_template(self, output_path: str) -> bool:
+        """
+        Create a reference DOCX template that can be modified for styling.
+
+        Args:
+            output_path (str): Path where the template should be saved
+
+        Returns:
+            bool: True if template was created successfully, False otherwise
+        """
+        try:
+            cmd = ["pandoc", "--print-default-data-file", "reference.docx"]
+
+            with open(output_path, "wb") as f:
+                result = subprocess.run(cmd, stdout=f, check=True)
+            return True
+        except subprocess.CalledProcessError as e:
+            print(f"Error creating template: {e.stderr}")
+            return False

edsl/results/MarkdownToPDF.py

@@ -0,0 +1,111 @@
+from typing import Optional
+import subprocess
+import os
+from pathlib import Path
+import tempfile
+
+
+class MarkdownToPDF:
+    def __init__(self, markdown_content: str, filename: Optional[str] = None):
+        """
+        Initialize the converter with markdown content.
+
+        Args:
+            markdown_content (str): The markdown content to be converted
+        """
+        self.markdown_content = markdown_content
+        self.filename = filename
+        self._check_pandoc()
+        # self.convert()
+
+    def _check_pandoc(self):
+        """Check if pandoc is installed and accessible."""
+        try:
+            subprocess.run(["pandoc", "--version"], capture_output=True, check=True)
+        except (subprocess.CalledProcessError, FileNotFoundError):
+            raise RuntimeError(
+                "Pandoc is not installed or not found in PATH. "
+                "Please install pandoc before using this converter."
+            )
+
+    def convert(self, output_path: str, **options) -> bool:
+        """
+        Convert the markdown content to PDF.
+
+        Args:
+            output_path (str): Path where the PDF should be saved
+            **options: Additional conversion options
+                margin (str): Page margin (default: "1in")
+                font_size (str): Font size (default: "12pt")
+                toc (bool): Include table of contents (default: False)
+                number_sections (bool): Number sections (default: False)
+                highlight_style (str): Code highlighting style (default: "tango")
+
+        Returns:
+            bool: True if conversion was successful, False otherwise
+        """
+        # Ensure output directory exists
+        output_path = Path(output_path)
+        output_path.parent.mkdir(parents=True, exist_ok=True)
+
+        # Build pandoc command with default options
+        cmd = [
+            "pandoc",
+            "-f",
+            "markdown",
+            "-o",
+            str(output_path),
+            "--pdf-engine=xelatex",
+            "--variable",
+            f'geometry:margin={options.get("margin", "1in")}',
+            "--variable",
+            f'fontsize={options.get("font_size", "12pt")}',
+        ]
+
+        # Add font only if specifically provided
+        if "font" in options:
+            cmd.extend(["--variable", f'mainfont={options["font"]}'])
+
+        # Add optional parameters
+        if options.get("toc", False):
+            cmd.append("--toc")
+
+        if options.get("number_sections", False):
+            cmd.append("--number-sections")
+
+        if "highlight_style" in options:
+            cmd.extend(["--highlight-style", options["highlight_style"]])
+
+        try:
+            # Run pandoc command
+            result = subprocess.run(
+                cmd,
+                input=self.markdown_content,
+                text=True,
+                capture_output=True,
+                check=True,
+            )
+            return True
+        except subprocess.CalledProcessError as e:
+            print(f"Error converting markdown to PDF: {e.stderr}")
+            return False
+
+    def preview(self) -> str:
+        """
+        Generate a temporary PDF and return its path.
+
+        Returns:
+            str: Path to the temporary PDF file
+        """
+        temp_dir = tempfile.mkdtemp()
+        if self.filename:
+            temp_pdf = os.path.join(temp_dir, f"{self.filename}.pdf")
+        else:
+            temp_pdf = os.path.join(temp_dir, "preview.pdf")
+
+        if self.convert(temp_pdf):
+            from edsl.scenarios.FileStore import FileStore
+
+            return FileStore(temp_pdf)
+
+        return None