markdown-to-confluence 0.2.0__py3-none-any.whl → 0.2.1__py3-none-any.whl

{markdown_to_confluence-0.2.0.dist-info → markdown_to_confluence-0.2.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: markdown-to-confluence
-Version: 0.2.0
+Version: 0.2.1
 Summary: Publish Markdown files to Confluence wiki
 Home-page: https://github.com/hunyadi/md2conf
 Author: Levente Hunyadi
@@ -51,7 +51,7 @@ This Python package
 * Image references (uploaded as Confluence page attachments)
 * Tables
 * [Table of contents](https://docs.gitlab.com/ee/user/markdown.html#table-of-contents)
-* [Admonitions](https://python-markdown.github.io/extensions/admonition/) and [alerts](https://docs.github.com/en/get-started/writing-on-github/getting-started-with-writing-and-formatting-on-github/basic-writing-and-formatting-syntax#alerts)
+* [Admonitions](https://python-markdown.github.io/extensions/admonition/) and alert boxes in [GitHub](https://docs.github.com/en/get-started/writing-on-github/getting-started-with-writing-and-formatting-on-github/basic-writing-and-formatting-syntax#alerts) and [GitLab](https://docs.gitlab.com/ee/development/documentation/styleguide/#alert-boxes)
 * [Collapsed sections](https://docs.github.com/en/get-started/writing-on-github/working-with-advanced-formatting/organizing-information-with-collapsed-sections)
 * [Mermaid diagrams](https://mermaid.live/) in code blocks (converted to images)
 
@@ -149,16 +149,17 @@ Alternatively, use the `--generated-by GENERATED_BY` option. The tag takes prece
 You execute the command-line tool `md2conf` to synchronize the Markdown file with Confluence:
 
 ```sh
-$ python3 -m md2conf sample/example.md
+$ python3 -m md2conf sample/index.md
 ```
 
 Use the `--help` switch to get a full list of supported command-line options:
 
 ```console
 $ python3 -m md2conf --help
-usage: md2conf [-h] [-d DOMAIN] [-p PATH] [-u USERNAME] [-a APIKEY] [-s SPACE] [-l {debug,info,warning,error,critical}] [-r ROOT_PAGE]
-               [--generated-by GENERATED_BY] [--no-generated-by] [--render-mermaid] [--no-render-mermaid]
-               [--render-mermaid-format {png,svg}] [--heading-anchors] [--ignore-invalid-url] [--local]
+usage: md2conf [-h] [--version] [-d DOMAIN] [-p PATH] [-u USERNAME] [-a APIKEY] [-s SPACE]
+               [-l {debug,info,warning,error,critical}] [-r ROOT_PAGE] [--generated-by GENERATED_BY] [--no-generated-by]
+               [--render-mermaid] [--no-render-mermaid] [--render-mermaid-format {png,svg}] [--heading-anchors]
+               [--ignore-invalid-url] [--local] [--headers [KEY=VALUE ...]] [--webui-links]
                mdpath
 
 positional arguments:
@@ -166,6 +167,7 @@ positional arguments:
 
 options:
   -h, --help            show this help message and exit
+  --version             show program's version number and exit
   -d DOMAIN, --domain DOMAIN
                         Confluence organization domain.
   -p PATH, --path PATH  Base path for Confluence (default: '/wiki/').
@@ -188,6 +190,9 @@ options:
   --heading-anchors     Place an anchor at each section heading with GitHub-style same-page identifiers.
   --ignore-invalid-url  Emit a warning but otherwise ignore relative URLs that point to ill-specified locations.
   --local               Write XHTML-based Confluence Storage Format files locally without invoking Confluence API.
+  --headers [KEY=VALUE ...]
+                        Apply custom headers to all Confluence API requests.
+  --webui-links         Enable Confluence Web UI links.
 ```
 
 ### Using the docker container

markdown_to_confluence-0.2.1.dist-info/RECORD

@@ -0,0 +1,17 @@
+md2conf/__init__.py,sha256=xyEemQnRFIqHO1wvcc3eovTSr1CDUve26Sq0msXUIZw,402
+md2conf/__main__.py,sha256=_qUspNQmQdhpH4Myh9vXDcauPyUx_FyEzNtaW_c8ytY,6601
+md2conf/api.py,sha256=UZ7mkeE1d_f_bACj8LC-t6d4EqXFQCufbeVVdi4FsTs,16947
+md2conf/application.py,sha256=W5OV86XbHWP1qqmJAcRvHPH7NpKQE6yF6nlGpN6RmoU,7709
+md2conf/converter.py,sha256=_zFk-H4NZuY2Y58enVGgFNubOJv9EI2u8tS7RQRiD3A,30391
+md2conf/entities.dtd,sha256=M6NzqL5N7dPs_eUA_6sDsiSLzDaAacrx9LdttiufvYU,30215
+md2conf/mermaid.py,sha256=3zawPXHXkCDhEK-WNtCH-gTqsLBDRzLrmlSo8ZW-Ii8,1371
+md2conf/processor.py,sha256=Tx8t7S8Wl1a4rgMvn2-qw8ob9Q5w2L81a0mfqFYmRJg,3963
+md2conf/properties.py,sha256=2l1tW8HmnrEsXN4-Dtby2tYJQTG1MirRpM3H6ykjQ4c,1858
+md2conf/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+markdown_to_confluence-0.2.1.dist-info/LICENSE,sha256=Pv43so2bPfmKhmsrmXFyAvS7M30-1i1tzjz6-dfhyOo,1077
+markdown_to_confluence-0.2.1.dist-info/METADATA,sha256=AiazDLT-VIO7txFz-lJvvCA0ckVfPNjXNXHV6csWOl4,10422
+markdown_to_confluence-0.2.1.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
+markdown_to_confluence-0.2.1.dist-info/entry_points.txt,sha256=F1zxa1wtEObtbHS-qp46330WVFLHdMnV2wQ-ZorRmX0,50
+markdown_to_confluence-0.2.1.dist-info/top_level.txt,sha256=_FJfl_kHrHNidyjUOuS01ngu_jDsfc-ZjSocNRJnTzU,8
+markdown_to_confluence-0.2.1.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
+markdown_to_confluence-0.2.1.dist-info/RECORD,,

md2conf/__init__.py

@@ -5,7 +5,7 @@ Parses Markdown files, converts Markdown content into the Confluence Storage For
 Confluence API endpoints to upload images and content.
 """
 
-__version__ = "0.2.0"
+__version__ = "0.2.1"
 __author__ = "Levente Hunyadi"
 __copyright__ = "Copyright 2022-2024, Levente Hunyadi"
 __license__ = "MIT"

md2conf/__main__.py

@@ -2,11 +2,13 @@ import argparse
 import logging
 import os.path
 import sys
+import typing
 from pathlib import Path
-from typing import Optional
+from typing import Any, Literal, Optional, Sequence, Union
 
 import requests
 
+from . import __version__
 from .api import ConfluenceAPI
 from .application import Application
 from .converter import ConfluenceDocumentOptions
@@ -24,12 +26,37 @@ class Arguments(argparse.Namespace):
     loglevel: str
     ignore_invalid_url: bool
     heading_anchors: bool
+    root_page: Optional[str]
     generated_by: Optional[str]
+    render_mermaid: bool
+    diagram_output_format: Literal["png", "svg"]
+    webui_links: bool
+
+
+class KwargsAppendAction(argparse.Action):
+    """Append key-value pairs to a dictionary"""
+
+    def __call__(
+        self,
+        parser: argparse.ArgumentParser,
+        namespace: argparse.Namespace,
+        values: Union[None, str, Sequence[Any]],
+        option_string: Optional[str] = None,
+    ) -> None:
+        try:
+            d = dict(map(lambda x: x.split("="), typing.cast(Sequence[str], values)))
+        except ValueError:
+            raise argparse.ArgumentError(
+                self,
+                f'Could not parse argument "{values}". It should follow the format: k1=v1 k2=v2 ...',
+            )
+        setattr(namespace, self.dest, d)
 
 
 def main() -> None:
     parser = argparse.ArgumentParser()
     parser.prog = os.path.basename(os.path.dirname(__file__))
+    parser.add_argument("--version", action="version", version=__version__)
     parser.add_argument(
         "mdpath", help="Path to Markdown file or directory to convert and publish."
     )
@@ -119,6 +146,20 @@ def main() -> None:
         default=False,
         help="Write XHTML-based Confluence Storage Format files locally without invoking Confluence API.",
     )
+    parser.add_argument(
+        "--headers",
+        nargs="*",
+        required=False,
+        action=KwargsAppendAction,
+        metavar="KEY=VALUE",
+        help="Apply custom headers to all Confluence API requests.",
+    )
+    parser.add_argument(
+        "--webui-links",
+        action="store_true",
+        default=False,
+        help="Enable Confluence Web UI links.",
+    )
 
     args = Arguments()
     parser.parse_args(namespace=args)
@@ -139,9 +180,10 @@ def main() -> None:
         root_page_id=args.root_page,
         render_mermaid=args.render_mermaid,
         diagram_output_format=args.diagram_output_format,
+        webui_links=args.webui_links,
     )
     properties = ConfluenceProperties(
-        args.domain, args.path, args.username, args.apikey, args.space
+        args.domain, args.path, args.username, args.apikey, args.space, args.headers
     )
     if args.local:
         Processor(options, properties).process(args.mdpath)

md2conf/api.py

@@ -98,6 +98,10 @@ class ConfluenceAPI:
             session.headers.update(
                 {"Authorization": f"Bearer {self.properties.api_key}"}
             )
+
+        if self.properties.headers:
+            session.headers.update(self.properties.headers)
+
         self.session = ConfluenceSession(
             session,
             self.properties.domain,
@@ -352,6 +356,34 @@ class ConfluenceSession:
             content=typing.cast(str, storage["value"]),
         )
 
+    def get_page_ancestors(
+        self, page_id: str, *, space_key: Optional[str] = None
+    ) -> Dict[str, str]:
+        """
+        Retrieve Confluence wiki page ancestors.
+
+        :param page_id: The Confluence page ID.
+        :param space_key: The Confluence space key (unless the default space is to be used).
+        :returns: Dictionary of ancestor page ID to title, with topmost ancestor first.
+        """
+
+        path = f"/content/{page_id}"
+        query = {
+            "spaceKey": space_key or self.space_key,
+            "expand": "ancestors",
+        }
+        data = typing.cast(Dict[str, JsonType], self._invoke(path, query))
+        ancestors = typing.cast(List[JsonType], data["ancestors"])
+
+        # from the JSON array of ancestors, extract the "id" and "title"
+        results: Dict[str, str] = {}
+        for node in ancestors:
+            ancestor = typing.cast(Dict[str, JsonType], node)
+            id = typing.cast(str, ancestor["id"])
+            title = typing.cast(str, ancestor["title"])
+            results[id] = title
+        return results
+
     def get_page_version(
         self,
         page_id: str,

md2conf/application.py

@@ -1,15 +1,17 @@
 import logging
 import os.path
 from pathlib import Path
-from typing import Dict, Optional
+from typing import Dict, List, Optional
 
-from .api import ConfluenceSession
+from .api import ConfluencePage, ConfluenceSession
 from .converter import (
     ConfluenceDocument,
     ConfluenceDocumentOptions,
     ConfluencePageMetadata,
+    ConfluenceQualifiedID,
     attachment_name,
     extract_qualified_id,
+    read_qualified_id,
 )
 
 LOGGER = logging.getLogger(__name__)
@@ -45,28 +47,19 @@ class Application:
     def synchronize_directory(self, local_dir: Path) -> None:
         "Synchronizes a directory of Markdown pages with Confluence."
 
-        page_metadata: Dict[Path, ConfluencePageMetadata] = {}
         LOGGER.info(f"Synchronizing directory: {local_dir}")
 
         # Step 1: build index of all page metadata
-        # NOTE: Pathlib.walk() is implemented only in Python 3.12+
-        # so sticking for old os.walk
-        for root, directories, files in os.walk(local_dir):
-            for file_name in files:
-                # Reconstitute Path object back
-                docfile = (Path(root) / file_name).absolute()
-
-                # Skip non-markdown files
-                if docfile.suffix.lower() != ".md":
-                    continue
-                metadata = self._get_or_create_page(docfile)
-
-                LOGGER.debug(f"indexed {docfile} with metadata: {metadata}")
-                page_metadata[docfile] = metadata
-
-        LOGGER.info(f"indexed {len(page_metadata)} pages")
+        page_metadata: Dict[Path, ConfluencePageMetadata] = {}
+        root_id = (
+            ConfluenceQualifiedID(self.options.root_page_id, self.api.space_key)
+            if self.options.root_page_id
+            else None
+        )
+        self._index_directory(local_dir, root_id, page_metadata)
+        LOGGER.info(f"indexed {len(page_metadata)} page(s)")
 
-        # Step 2: Convert each page
+        # Step 2: convert each page
         for page_path in page_metadata.keys():
             self._synchronize_page(page_path, page_metadata)
 
@@ -86,8 +79,51 @@ class Application:
         else:
             self._update_document(document, base_path)
 
+    def _index_directory(
+        self,
+        local_dir: Path,
+        root_id: Optional[ConfluenceQualifiedID],
+        page_metadata: Dict[Path, ConfluencePageMetadata],
+    ) -> None:
+        "Indexes Markdown files in a directory recursively."
+
+        LOGGER.info(f"Indexing directory: {local_dir}")
+
+        files: List[Path] = []
+        directories: List[Path] = []
+        for entry in os.scandir(local_dir):
+            if entry.is_file():
+                if entry.name.endswith(".md"):
+                    # skip non-markdown files
+                    files.append((Path(local_dir) / entry.name).absolute())
+            elif entry.is_dir():
+                if not entry.name.startswith("."):
+                    directories.append((Path(local_dir) / entry.name).absolute())
+
+        # make page act as parent node in Confluence
+        parent_id: Optional[ConfluenceQualifiedID] = None
+        if "index.md" in files:
+            parent_id = read_qualified_id(Path(local_dir) / "index.md")
+        elif "README.md" in files:
+            parent_id = read_qualified_id(Path(local_dir) / "README.md")
+
+        if parent_id is None:
+            parent_id = root_id
+
+        for doc in files:
+            metadata = self._get_or_create_page(doc, parent_id)
+            LOGGER.debug(f"indexed {doc} with metadata: {metadata}")
+            page_metadata[doc] = metadata
+
+        for directory in directories:
+            self._index_directory(Path(local_dir) / directory, parent_id, page_metadata)
+
     def _get_or_create_page(
-        self, absolute_path: Path, title: Optional[str] = None
+        self,
+        absolute_path: Path,
+        parent_id: Optional[ConfluenceQualifiedID],
+        *,
+        title: Optional[str] = None,
     ) -> ConfluencePageMetadata:
         """
         Creates a new Confluence page if no page is linked in the Markdown document.
@@ -103,23 +139,13 @@ class Application:
                 qualified_id.page_id, space_key=qualified_id.space_key
             )
         else:
-            if self.options.root_page_id is None:
+            if parent_id is None:
                 raise ValueError(
                     "expected: Confluence page ID to act as parent for Markdown files with no linked Confluence page"
                 )
 
-            # use file name without extension if no title is supplied
-            if title is None:
-                title = absolute_path.stem
-
-            confluence_page = self.api.get_or_create_page(
-                title, self.options.root_page_id
-            )
-            self._update_markdown(
-                absolute_path,
-                document,
-                confluence_page.id,
-                confluence_page.space_key,
+            confluence_page = self._create_page(
+                absolute_path, document, title, parent_id
             )
 
         return ConfluencePageMetadata(
@@ -130,7 +156,32 @@ class Application:
             title=confluence_page.title or "",
         )
 
+    def _create_page(
+        self,
+        absolute_path: Path,
+        document: str,
+        title: Optional[str],
+        parent_id: ConfluenceQualifiedID,
+    ) -> ConfluencePage:
+        "Creates a new Confluence page when Markdown file doesn't have an embedded page ID yet."
+
+        # use file name without extension if no title is supplied
+        if title is None:
+            title = absolute_path.stem
+
+        confluence_page = self.api.get_or_create_page(
+            title, parent_id.page_id, space_key=parent_id.space_key
+        )
+        self._update_markdown(
+            absolute_path,
+            document,
+            confluence_page.id,
+            confluence_page.space_key,
+        )
+        return confluence_page
+
     def _update_document(self, document: ConfluenceDocument, base_path: Path) -> None:
+        "Saves a new version of a Confluence document."
 
         for image in document.images:
             self.api.upload_attachment(
@@ -158,8 +209,23 @@ class Application:
         page_id: str,
         space_key: Optional[str],
     ) -> None:
+        "Writes the Confluence page ID and space key at the beginning of the Markdown file."
+
+        content: List[str] = []
+
+        # check if the file has frontmatter
+        index = 0
+        if document.startswith("---\n"):
+            index = document.find("\n---\n", 4) + 4
+
+            # insert the Confluence keys after the frontmatter
+            content.append(document[:index])
+
+        content.append(f"<!-- confluence-page-id: {page_id} -->")
+        if space_key:
+            content.append(f"<!-- confluence-space-key: {space_key} -->")
+
+        content.append(document[index:])
+
         with open(path, "w", encoding="utf-8") as file:
-            file.write(f"<!-- confluence-page-id: {page_id} -->\n")
-            if space_key:
-                file.write(f"<!-- confluence-space-key: {space_key} -->\n")
-            file.write(document)
+            file.write("\n".join(content))

md2conf/converter.py

@@ -4,11 +4,11 @@ import hashlib
 import importlib.resources as resources
 import logging
 import os.path
-import pathlib
 import re
 import sys
 import uuid
 from dataclasses import dataclass
+from pathlib import Path
 from typing import Dict, List, Literal, Optional, Tuple
 from urllib.parse import ParseResult, urlparse, urlunparse
 
@@ -36,6 +36,15 @@ class ParseError(RuntimeError):
     pass
 
 
+def starts_with_any(text: str, prefixes: List[str]) -> bool:
+    "True if text starts with any of the listed prefixes."
+
+    for prefix in prefixes:
+        if text.startswith(prefix):
+            return True
+    return False
+
+
 def is_absolute_url(url: str) -> bool:
     urlparts = urlparse(url)
     return bool(urlparts.scheme) or bool(urlparts.netloc)
@@ -61,7 +70,7 @@ def markdown_to_html(content: str) -> str:
     )
 
 
-def _elements_from_strings(dtd_path: pathlib.Path, items: List[str]) -> ET._Element:
+def _elements_from_strings(dtd_path: Path, items: List[str]) -> ET._Element:
     """
     Creates a fragment of several XML nodes from their string representation wrapped in a root element.
 
@@ -240,30 +249,32 @@ class ConfluenceConverterOptions:
         conversion rules for the identifier.
     :param render_mermaid: Whether to pre-render Mermaid diagrams into PNG/SVG images.
     :param diagram_output_format: Target image format for diagrams.
+    :param web_links: When true, convert relative URLs to Confluence Web UI links.
     """
 
     ignore_invalid_url: bool = False
     heading_anchors: bool = False
     render_mermaid: bool = False
     diagram_output_format: Literal["png", "svg"] = "png"
+    webui_links: bool = False
 
 
 class ConfluenceStorageFormatConverter(NodeVisitor):
     "Transforms a plain HTML tree into the Confluence storage format."
 
     options: ConfluenceConverterOptions
-    path: pathlib.Path
-    base_path: pathlib.Path
+    path: Path
+    base_path: Path
     links: List[str]
     images: List[str]
     embedded_images: Dict[str, bytes]
-    page_metadata: Dict[pathlib.Path, ConfluencePageMetadata]
+    page_metadata: Dict[Path, ConfluencePageMetadata]
 
     def __init__(
         self,
         options: ConfluenceConverterOptions,
-        path: pathlib.Path,
-        page_metadata: Dict[pathlib.Path, ConfluencePageMetadata],
+        path: Path,
+        page_metadata: Dict[Path, ConfluencePageMetadata],
     ) -> None:
         super().__init__()
         self.options = options
@@ -347,10 +358,15 @@ class ConfluenceStorageFormatConverter(NodeVisitor):
         )
         self.links.append(url)
 
+        if self.options.webui_links:
+            page_url = f"{link_metadata.base_path}pages/viewpage.action?pageId={link_metadata.page_id}"
+        else:
+            page_url = f"{link_metadata.base_path}spaces/{link_metadata.space_key}/pages/{link_metadata.page_id}/{link_metadata.title}"
+
         components = ParseResult(
             scheme="https",
             netloc=link_metadata.domain,
-            path=f"{link_metadata.base_path}spaces/{link_metadata.space_key}/pages/{link_metadata.page_id}/{link_metadata.title}",
+            path=page_url,
             params="",
             query="",
             fragment=relative_url.fragment,
@@ -365,7 +381,7 @@ class ConfluenceStorageFormatConverter(NodeVisitor):
 
         # prefer PNG over SVG; Confluence displays SVG in wrong size, and text labels are truncated
         if path and is_relative_url(path):
-            relative_path = pathlib.Path(path)
+            relative_path = Path(path)
             if (
                 relative_path.suffix == ".svg"
                 and (self.base_path / relative_path.with_suffix(".png")).exists()
@@ -541,43 +557,83 @@ class ConfluenceStorageFormatConverter(NodeVisitor):
             *content,
         )
 
-    def _transform_alert(self, elem: ET._Element) -> ET._Element:
+    def _transform_github_alert(self, elem: ET._Element) -> ET._Element:
+        content = elem[0]
+        if content.text is None:
+            raise DocumentError("empty content")
+
+        class_name: Optional[str] = None
+        skip = 0
+
+        pattern = re.compile(r"^\[!([A-Z]+)\]\s*")
+        match = pattern.match(content.text)
+        if match:
+            skip = len(match.group(0))
+            alert = match.group(1)
+            if alert == "NOTE":
+                class_name = "note"
+            elif alert == "TIP":
+                class_name = "tip"
+            elif alert == "IMPORTANT":
+                class_name = "tip"
+            elif alert == "WARNING":
+                class_name = "warning"
+            elif alert == "CAUTION":
+                class_name = "warning"
+            else:
+                raise DocumentError(f"unsupported GitHub alert: {alert}")
+
+        return self._transform_alert(elem, class_name, skip)
+
+    def _transform_gitlab_alert(self, elem: ET._Element) -> ET._Element:
+        content = elem[0]
+        if content.text is None:
+            raise DocumentError("empty content")
+
+        class_name: Optional[str] = None
+        skip = 0
+
+        pattern = re.compile(r"^(FLAG|NOTE|WARNING|DISCLAIMER):\s*")
+        match = pattern.match(content.text)
+        if match:
+            skip = len(match.group(0))
+            alert = match.group(1)
+            if alert == "FLAG":
+                class_name = "note"
+            elif alert == "NOTE":
+                class_name = "note"
+            elif alert == "WARNING":
+                class_name = "warning"
+            elif alert == "DISCLAIMER":
+                class_name = "info"
+            else:
+                raise DocumentError(f"unsupported GitLab alert: {alert}")
+
+        return self._transform_alert(elem, class_name, skip)
+
+    def _transform_alert(
+        self, elem: ET._Element, class_name: Optional[str], skip: int
+    ) -> ET._Element:
         """
-        Creates an info, tip, note or warning panel from a GitHub alert.
+        Creates an info, tip, note or warning panel from a GitHub or GitLab alert.
 
         Transforms
-        [GitHub alert](https://docs.github.com/en/get-started/writing-on-github/getting-started-with-writing-and-formatting-on-github/basic-writing-and-formatting-syntax#alerts)  # noqa: E501 # no way to make this link shorter
+        [GitHub alert](https://docs.github.com/get-started/writing-on-github/getting-started-with-writing-and-formatting-on-github/basic-writing-and-formatting-syntax#alerts)
+        or [GitLab alert](https://docs.gitlab.com/ee/development/documentation/styleguide/#alert-boxes)
         syntax into one of the Confluence structured macros *info*, *tip*, *note*, or *warning*.
         """
 
-        pattern = re.compile(r"^\[!([A-Z]+)\]\s*")
-
         content = elem[0]
         if content.text is None:
             raise DocumentError("empty content")
 
-        match = pattern.match(content.text)
-        if match is None:
+        if class_name is None:
             raise DocumentError("not an alert")
-        alert = match.group(1)
-
-        if alert == "NOTE":
-            class_name = "note"
-        elif alert == "TIP":
-            class_name = "tip"
-        elif alert == "IMPORTANT":
-            class_name = "tip"
-        elif alert == "WARNING":
-            class_name = "warning"
-        elif alert == "CAUTION":
-            class_name = "warning"
-        else:
-            raise DocumentError(f"unsupported alert: {alert}")
 
         for e in elem:
             self.visit(e)
 
-        content.text = pattern.sub("", content.text, count=1)
+        content.text = content.text[skip:]
         return AC(
             "structured-macro",
             {
@@ -671,7 +727,22 @@ class ConfluenceStorageFormatConverter(NodeVisitor):
             and child[0].text is not None
             and child[0].text.startswith("[!")
         ):
-            return self._transform_alert(child)
+            return self._transform_github_alert(child)
+
+        # Alerts in GitLab
+        # <blockquote>
+        #   <p>DISCLAIMER: ...</p>
+        # </blockquote>
+        elif (
+            child.tag == "blockquote"
+            and len(child) > 0
+            and child[0].tag == "p"
+            and child[0].text is not None
+            and starts_with_any(
+                child[0].text, ["FLAG:", "NOTE:", "WARNING:", "DISCLAIMER:"]
+            )
+        ):
+            return self._transform_gitlab_alert(child)
 
         # <details markdown="1">
         # <summary>...</summary>
@@ -726,8 +797,14 @@ class ConfluenceQualifiedID:
     page_id: str
     space_key: Optional[str] = None
 
+    def __init__(self, page_id: str, space_key: Optional[str] = None):
+        self.page_id = page_id
+        self.space_key = space_key
+
 
 def extract_qualified_id(string: str) -> Tuple[Optional[ConfluenceQualifiedID], str]:
+    "Extracts the Confluence page ID and space key from a Markdown document."
+
     page_id, string = extract_value(r"<!--\s+confluence-page-id:\s*(\d+)\s+-->", string)
 
     if page_id is None:
@@ -741,6 +818,16 @@ def extract_qualified_id(string: str) -> Tuple[Optional[ConfluenceQualifiedID],
     return ConfluenceQualifiedID(page_id, space_key), string
 
 
+def read_qualified_id(absolute_path: Path) -> Optional[ConfluenceQualifiedID]:
+    "Reads the Confluence page ID and space key from a Markdown document."
+
+    with open(absolute_path, "r", encoding="utf-8") as f:
+        document = f.read()
+
+    qualified_id, _ = extract_qualified_id(document)
+    return qualified_id
+
+
 @dataclass
 class ConfluenceDocumentOptions:
     """
@@ -754,6 +841,7 @@ class ConfluenceDocumentOptions:
     :param show_generated: Whether to display a prompt "This page has been generated with a tool."
     :param render_mermaid: Whether to pre-render Mermaid diagrams into PNG/SVG images.
     :param diagram_output_format: Target image format for diagrams.
+    :param webui_links: When true, convert relative URLs to Confluence Web UI links.
     """
 
     ignore_invalid_url: bool = False
@@ -762,6 +850,7 @@ class ConfluenceDocumentOptions:
     root_page_id: Optional[str] = None
     render_mermaid: bool = False
     diagram_output_format: Literal["png", "svg"] = "png"
+    webui_links: bool = False
 
 
 class ConfluenceDocument:
@@ -774,9 +863,9 @@ class ConfluenceDocument:
 
     def __init__(
         self,
-        path: pathlib.Path,
+        path: Path,
         options: ConfluenceDocumentOptions,
-        page_metadata: Dict[pathlib.Path, ConfluencePageMetadata],
+        page_metadata: Dict[Path, ConfluencePageMetadata],
     ) -> None:
         self.options = options
         path = path.absolute()
@@ -786,6 +875,13 @@ class ConfluenceDocument:
 
         # extract Confluence page ID
         qualified_id, text = extract_qualified_id(text)
+        if qualified_id is None:
+            # look up Confluence page ID in metadata
+            metadata = page_metadata.get(path)
+            if metadata is not None:
+                qualified_id = ConfluenceQualifiedID(
+                    metadata.page_id, metadata.space_key
+                )
         if qualified_id is None:
             raise ValueError("missing Confluence page ID")
         self.id = qualified_id
@@ -823,6 +919,7 @@ class ConfluenceDocument:
                 heading_anchors=self.options.heading_anchors,
                 render_mermaid=self.options.render_mermaid,
                 diagram_output_format=self.options.diagram_output_format,
+                webui_links=self.options.webui_links,
             ),
             path,
             page_metadata,

md2conf/processor.py

@@ -1,12 +1,14 @@
+import hashlib
 import logging
 import os
 from pathlib import Path
-from typing import Dict
+from typing import Dict, List
 
 from .converter import (
     ConfluenceDocument,
     ConfluenceDocumentOptions,
     ConfluencePageMetadata,
+    ConfluenceQualifiedID,
     extract_qualified_id,
 )
 from .properties import ConfluenceProperties
@@ -37,28 +39,14 @@ class Processor:
     def process_directory(self, local_dir: Path) -> None:
         "Recursively scans a directory hierarchy for Markdown files."
 
-        page_metadata: Dict[Path, ConfluencePageMetadata] = {}
         LOGGER.info(f"Synchronizing directory: {local_dir}")
 
         # Step 1: build index of all page metadata
-        # NOTE: Pathlib.walk() is implemented only in Python 3.12+
-        # so sticking for old os.walk
-        for root, directories, files in os.walk(local_dir):
-            for file_name in files:
-                # Reconstitute Path object back
-                docfile = (Path(root) / file_name).absolute()
-
-                # Skip non-markdown files
-                if docfile.suffix.lower() != ".md":
-                    continue
-
-                metadata = self._get_page(docfile)
-                LOGGER.debug(f"indexed {docfile} with metadata: {metadata}")
-                page_metadata[docfile] = metadata
-
-        LOGGER.info(f"indexed {len(page_metadata)} pages")
+        page_metadata: Dict[Path, ConfluencePageMetadata] = {}
+        self._index_directory(local_dir, page_metadata)
+        LOGGER.info(f"indexed {len(page_metadata)} page(s)")
 
-        # Step 2: Convert each page
+        # Step 2: convert each page
         for page_path in page_metadata.keys():
             self.process_page(page_path, page_metadata)
 
@@ -72,6 +60,34 @@ class Processor:
         with open(path.with_suffix(".csf"), "w", encoding="utf-8") as f:
             f.write(content)
 
+    def _index_directory(
+        self,
+        local_dir: Path,
+        page_metadata: Dict[Path, ConfluencePageMetadata],
+    ) -> None:
+        "Indexes Markdown files in a directory recursively."
+
+        LOGGER.info(f"Indexing directory: {local_dir}")
+
+        files: List[Path] = []
+        directories: List[Path] = []
+        for entry in os.scandir(local_dir):
+            if entry.is_file():
+                if entry.name.endswith(".md"):
+                    # skip non-markdown files
+                    files.append((Path(local_dir) / entry.name).absolute())
+            elif entry.is_dir():
+                if not entry.name.startswith("."):
+                    directories.append((Path(local_dir) / entry.name).absolute())
+
+        for doc in files:
+            metadata = self._get_page(doc)
+            LOGGER.debug(f"indexed {doc} with metadata: {metadata}")
+            page_metadata[doc] = metadata
+
+        for directory in directories:
+            self._index_directory(Path(local_dir) / directory, page_metadata)
+
     def _get_page(self, absolute_path: Path) -> ConfluencePageMetadata:
         "Extracts metadata from a Markdown file."
 
@@ -80,7 +96,13 @@ class Processor:
 
         qualified_id, document = extract_qualified_id(document)
         if qualified_id is None:
-            raise ValueError("required: page ID for local output")
+            if self.options.root_page_id is not None:
+                hash = hashlib.md5(document.encode("utf-8"))
+                digest = "".join(f"{c:x}" for c in hash.digest())
+                LOGGER.info(f"Identifier '{digest}' assigned to page: {absolute_path}")
+                qualified_id = ConfluenceQualifiedID(digest)
+            else:
+                raise ValueError("required: page ID for local output")
 
         return ConfluencePageMetadata(
             domain=self.properties.domain,

md2conf/properties.py

@@ -1,5 +1,5 @@
 import os
-from typing import Optional
+from typing import Dict, Optional
 
 
 class ConfluenceError(RuntimeError):
@@ -12,6 +12,7 @@ class ConfluenceProperties:
     space_key: str
     user_name: Optional[str]
     api_key: str
+    headers: Optional[Dict[str, str]]
 
     def __init__(
         self,
@@ -20,6 +21,7 @@ class ConfluenceProperties:
         user_name: Optional[str] = None,
         api_key: Optional[str] = None,
         space_key: Optional[str] = None,
+        headers: Optional[Dict[str, str]] = None,
     ) -> None:
         opt_domain = domain or os.getenv("CONFLUENCE_DOMAIN")
         opt_base_path = base_path or os.getenv("CONFLUENCE_PATH")
@@ -48,5 +50,4 @@ class ConfluenceProperties:
         self.user_name = opt_user_name
         self.api_key = opt_api_key
         self.space_key = opt_space_key
-        self.space_key = opt_space_key
-        self.space_key = opt_space_key
+        self.headers = headers

markdown_to_confluence-0.2.0.dist-info/RECORD

@@ -1,17 +0,0 @@
-md2conf/__init__.py,sha256=1KRpqiilQTkQz-oL8-HFPnI_6_3-_H0dq-SxQxDw56s,402
-md2conf/__main__.py,sha256=tWMEA_spxUTNNgViHtjsA85NzJixX-0G2zCq8BO3y_E,5230
-md2conf/api.py,sha256=Oc4FAQBNs85U8s-lbY0XwLBUcjm3Sd0_W59N4H3XAnE,15768
-md2conf/application.py,sha256=NnF84-cdW2cZUbU6VeHvuEg6g5NL5M9o2cpOSU7uv7o,5548
-md2conf/converter.py,sha256=XY7D8zpsVS7_PZzywciQ5YT2SHH5t1udPU5s2aPsmqs,27040
-md2conf/entities.dtd,sha256=M6NzqL5N7dPs_eUA_6sDsiSLzDaAacrx9LdttiufvYU,30215
-md2conf/mermaid.py,sha256=3zawPXHXkCDhEK-WNtCH-gTqsLBDRzLrmlSo8ZW-Ii8,1371
-md2conf/processor.py,sha256=3JZkbFtMjbtnQLEm6wFum96ldjZ9xNJuL8JjFadyGmg,3084
-md2conf/properties.py,sha256=oXvtPssbougM1BTE9ytcD_1Yjc3nd7DDSHqEr0QoZAU,1811
-md2conf/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-markdown_to_confluence-0.2.0.dist-info/LICENSE,sha256=Pv43so2bPfmKhmsrmXFyAvS7M30-1i1tzjz6-dfhyOo,1077
-markdown_to_confluence-0.2.0.dist-info/METADATA,sha256=nxwG4F2TX1do0lk38BCFIUMwqv6y2edErd2_5M-4la4,10023
-markdown_to_confluence-0.2.0.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
-markdown_to_confluence-0.2.0.dist-info/entry_points.txt,sha256=F1zxa1wtEObtbHS-qp46330WVFLHdMnV2wQ-ZorRmX0,50
-markdown_to_confluence-0.2.0.dist-info/top_level.txt,sha256=_FJfl_kHrHNidyjUOuS01ngu_jDsfc-ZjSocNRJnTzU,8
-markdown_to_confluence-0.2.0.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
-markdown_to_confluence-0.2.0.dist-info/RECORD,,