markdown-to-confluence 0.3.5__py3-none-any.whl → 0.4.0__py3-none-any.whl

md2conf/processor.py

@@ -6,20 +6,68 @@ Copyright 2022-2025, Levente Hunyadi
 :see: https://github.com/hunyadi/md2conf
 """
 
+import hashlib
 import logging
 import os
 from abc import abstractmethod
 from pathlib import Path
-from typing import Optional
+from typing import Iterable, Optional
 
+from .collection import ConfluencePageCollection
 from .converter import ConfluenceDocument, ConfluenceDocumentOptions, ConfluencePageID
 from .matcher import Matcher, MatcherOptions
-from .metadata import ConfluencePageMetadata, ConfluenceSiteMetadata
+from .metadata import ConfluenceSiteMetadata
 from .properties import ArgumentError
+from .scanner import Scanner
 
 LOGGER = logging.getLogger(__name__)
 
 
+class DocumentNode:
+    absolute_path: Path
+    page_id: Optional[str]
+    space_key: Optional[str]
+    title: Optional[str]
+
+    _children: list["DocumentNode"]
+
+    def __init__(
+        self,
+        absolute_path: Path,
+        page_id: Optional[str],
+        space_key: Optional[str] = None,
+        title: Optional[str] = None,
+    ):
+        self.absolute_path = absolute_path
+        self.page_id = page_id
+        self.space_key = space_key
+        self.title = title
+        self._children = []
+
+    def count(self) -> int:
+        c = len(self._children)
+        for child in self._children:
+            c += child.count()
+        return c
+
+    def add_child(self, child: "DocumentNode") -> None:
+        self._children.append(child)
+
+    def children(self) -> Iterable["DocumentNode"]:
+        for child in self._children:
+            yield child
+
+    def descendants(self) -> Iterable["DocumentNode"]:
+        for child in self._children:
+            yield child
+            yield from child.descendants()
+
+    def all(self) -> Iterable["DocumentNode"]:
+        yield self
+        for child in self._children:
+            yield from child.all()
+
+
 class Processor:
     """
     Processes a single Markdown page or a directory of Markdown pages.
@@ -29,7 +77,7 @@ class Processor:
     site: ConfluenceSiteMetadata
     root_dir: Path
 
-    page_metadata: dict[Path, ConfluencePageMetadata]
+    page_metadata: ConfluencePageCollection
 
     def __init__(
         self,
@@ -40,8 +88,7 @@ class Processor:
         self.options = options
         self.site = site
         self.root_dir = root_dir
-
-        self.page_metadata = {}
+        self.page_metadata = ConfluencePageCollection()
 
     def process_directory(self, local_dir: Path) -> None:
         """
@@ -51,13 +98,16 @@ class Processor:
         local_dir = local_dir.resolve(True)
         LOGGER.info("Processing directory: %s", local_dir)
 
-        # Step 1: build index of all page metadata
-        self._index_directory(local_dir, self.options.root_page_id)
-        LOGGER.info("Indexed %d page(s)", len(self.page_metadata))
+        # Step 1: build index of all Markdown files in directory hierarchy
+        root = self._index_directory(local_dir, None)
+        LOGGER.info("Indexed %d document(s)", root.count())
+
+        # Step 2: synchronize directory tree structure with page hierarchy in space
+        self._synchronize_tree(root, self.options.root_page_id)
 
-        # Step 2: convert each page
-        for page_path in self.page_metadata.keys():
-            self._process_page(page_path)
+        # Step 3: synchronize files in directory hierarchy with pages in space
+        for path, metadata in self.page_metadata.items():
+            self._synchronize_page(path, ConfluencePageID(metadata.page_id))
 
     def process_page(self, path: Path) -> None:
         """
@@ -65,32 +115,52 @@ class Processor:
         """
 
         LOGGER.info("Processing page: %s", path)
-        self._index_page(path, self.options.root_page_id)
-        self._process_page(path)
 
-    def _process_page(self, path: Path) -> None:
+        # Step 1: parse Markdown file
+        root = self._index_file(path)
+
+        # Step 2: find matching page in Confluence
+        self._synchronize_tree(root, self.options.root_page_id)
+
+        # Step 3: synchronize document with page in space
+        for path, metadata in self.page_metadata.items():
+            self._synchronize_page(path, ConfluencePageID(metadata.page_id))
+
+    def _synchronize_page(self, path: Path, page_id: ConfluencePageID) -> None:
+        """
+        Synchronizes a single Markdown document with its corresponding Confluence page.
+        """
+
         page_id, document = ConfluenceDocument.create(
             path, self.options, self.root_dir, self.site, self.page_metadata
         )
-        self._save_document(page_id, document, path)
+        self._update_page(page_id, document, path)
 
     @abstractmethod
-    def _get_or_create_page(
-        self, absolute_path: Path, parent_id: Optional[ConfluencePageID]
-    ) -> ConfluencePageMetadata:
+    def _synchronize_tree(
+        self, node: DocumentNode, page_id: Optional[ConfluencePageID]
+    ) -> None:
         """
-        Creates a new Confluence page if no page is linked in the Markdown document.
+        Creates the cross-reference index and synchronizes the directory tree structure with the Confluence page hierarchy.
+
+        Creates new Confluence pages as necessary, e.g. if no page is linked in the Markdown document, or no page is found with lookup by page title.
+
+        May update the original Markdown document to add tags to associate the document with its corresponding Confluence page.
         """
         ...
 
     @abstractmethod
-    def _save_document(
+    def _update_page(
         self, page_id: ConfluencePageID, document: ConfluenceDocument, path: Path
-    ) -> None: ...
+    ) -> None:
+        """
+        Saves the document as Confluence Storage Format XHTML.
+        """
+        ...
 
     def _index_directory(
-        self, local_dir: Path, parent_id: Optional[ConfluencePageID]
-    ) -> None:
+        self, local_dir: Path, parent: Optional[DocumentNode]
+    ) -> DocumentNode:
         """
         Indexes Markdown files in a directory hierarchy recursively.
         """
@@ -130,28 +200,54 @@ class Processor:
             if parent_doc in files:
                 files.remove(parent_doc)
 
-            # use latest parent as parent for index page
-            metadata = self._get_or_create_page(parent_doc, parent_id)
-            LOGGER.debug("Indexed parent %s with metadata: %s", parent_doc, metadata)
-            self.page_metadata[parent_doc] = metadata
-
-            # assign new index page as new parent
-            parent_id = ConfluencePageID(metadata.page_id)
-
-        for doc in files:
-            self._index_page(doc, parent_id)
+            # promote Markdown document in directory as parent page in Confluence
+            node = self._index_file(parent_doc)
+            if parent is not None:
+                parent.add_child(node)
+            parent = node
+        elif parent is None:
+            # create new top-level node
+            if self.options.root_page_id is not None:
+                page_id = self.options.root_page_id.page_id
+                parent = DocumentNode(local_dir, page_id=page_id)
+            else:
+                # local use only, raises error with remote synchronization
+                parent = DocumentNode(local_dir, page_id=None)
+
+        for file in files:
+            node = self._index_file(file)
+            parent.add_child(node)
 
         for directory in directories:
-            self._index_directory(directory, parent_id)
+            self._index_directory(directory, parent)
 
-    def _index_page(self, path: Path, parent_id: Optional[ConfluencePageID]) -> None:
+        return parent
+
+    def _index_file(self, path: Path) -> DocumentNode:
         """
         Indexes a single Markdown file.
         """
 
-        metadata = self._get_or_create_page(path, parent_id)
-        LOGGER.debug("Indexed %s with metadata: %s", path, metadata)
-        self.page_metadata[path] = metadata
+        LOGGER.info("Indexing file: %s", path)
+
+        # extract information from a Markdown document found in a local directory.
+        document = Scanner().read(path)
+
+        return DocumentNode(
+            absolute_path=path,
+            page_id=document.page_id,
+            space_key=document.space_key,
+            title=document.title,
+        )
+
+    def _generate_hash(self, absolute_path: Path) -> str:
+        """
+        Computes a digest to be used as a unique string.
+        """
+
+        relative_path = absolute_path.relative_to(self.root_dir)
+        hash = hashlib.md5(relative_path.as_posix().encode("utf-8"))
+        return "".join(f"{c:x}" for c in hash.digest())
 
 
 class ProcessorFactory:

md2conf/properties.py

@@ -54,15 +54,28 @@ class ConfluenceSiteProperties:
         self.space_key = opt_space_key
 
 
-class ConfluenceConnectionProperties(ConfluenceSiteProperties):
-    "Properties related to connecting to Confluence."
-
+class ConfluenceConnectionProperties:
+    """
+    Properties related to connecting to Confluence.
+
+    :param api_url: Confluence API URL. Required for scoped tokens.
+    :param user_name: Confluence user name.
+    :param api_key: Confluence API key.
+    :param headers: Additional HTTP headers to pass to Confluence REST API calls.
+    """
+
+    domain: Optional[str]
+    base_path: Optional[str]
+    space_key: Optional[str]
+    api_url: Optional[str]
     user_name: Optional[str]
     api_key: str
     headers: Optional[dict[str, str]]
 
     def __init__(
         self,
+        *,
+        api_url: Optional[str] = None,
         domain: Optional[str] = None,
         base_path: Optional[str] = None,
         user_name: Optional[str] = None,
@@ -70,14 +83,20 @@ class ConfluenceConnectionProperties(ConfluenceSiteProperties):
         space_key: Optional[str] = None,
         headers: Optional[dict[str, str]] = None,
     ) -> None:
-        super().__init__(domain, base_path, space_key)
-
+        opt_api_url = api_url or os.getenv("CONFLUENCE_API_URL")
+        opt_domain = domain or os.getenv("CONFLUENCE_DOMAIN")
+        opt_base_path = base_path or os.getenv("CONFLUENCE_PATH")
+        opt_space_key = space_key or os.getenv("CONFLUENCE_SPACE_KEY")
         opt_user_name = user_name or os.getenv("CONFLUENCE_USER_NAME")
         opt_api_key = api_key or os.getenv("CONFLUENCE_API_KEY")
 
         if not opt_api_key:
             raise ArgumentError("Confluence API key not specified")
 
+        self.api_url = opt_api_url
+        self.domain = opt_domain
+        self.base_path = opt_base_path
+        self.space_key = opt_space_key
         self.user_name = opt_user_name
         self.api_key = opt_api_key
         self.headers = headers

md2conf/scanner.py

@@ -9,15 +9,26 @@ Copyright 2022-2025, Levente Hunyadi
 import re
 from dataclasses import dataclass
 from pathlib import Path
-from typing import Any, Optional
+from typing import Any, Optional, TypeVar
 
 import yaml
+from strong_typing.core import JsonType
+from strong_typing.serialization import DeserializerOptions, json_to_object
+
+T = TypeVar("T")
+
+
+def _json_to_object(
+    typ: type[T],
+    data: JsonType,
+) -> T:
+    return json_to_object(typ, data, options=DeserializerOptions(skip_unassigned=True))
 
 
 def extract_value(pattern: str, text: str) -> tuple[Optional[str], str]:
     values: list[str] = []
 
-    def _repl_func(matchobj: re.Match) -> str:
+    def _repl_func(matchobj: re.Match[str]) -> str:
         values.append(matchobj.group(1))
         return ""
 
@@ -46,16 +57,27 @@ def extract_frontmatter_properties(text: str) -> tuple[Optional[dict[str, Any]],
     return properties, text
 
 
-def get_string(properties: dict[str, Any], key: str) -> Optional[str]:
-    value = properties.get(key)
-    if value is None:
-        return None
-    elif not isinstance(value, str):
-        raise ValueError(
-            f"expected dictionary value type of `str` for key `{key}`; got value of type `{type(value).__name__}`"
-        )
-    else:
-        return value
+@dataclass
+class DocumentProperties:
+    """
+    An object that holds properties extracted from the front-matter of a Markdown document.
+
+    :param page_id: Confluence page ID.
+    :param space_key: Confluence space key.
+    :param confluence_page_id: Confluence page ID. (Alternative name for JSON de-serialization.)
+    :param confluence_space_key: Confluence space key. (Alternative name for JSON de-serialization.)
+    :param generated_by: Text identifying the tool that generated the document.
+    :param title: The title extracted from front-matter.
+    :param tags: A list of tags (content labels) extracted from front-matter.
+    """
+
+    page_id: Optional[str]
+    space_key: Optional[str]
+    confluence_page_id: Optional[str]
+    confluence_space_key: Optional[str]
+    generated_by: Optional[str]
+    title: Optional[str]
+    tags: Optional[list[str]]
 
 
 @dataclass
@@ -67,6 +89,7 @@ class ScannedDocument:
     :param space_key: Confluence space key.
     :param generated_by: Text identifying the tool that generated the document.
     :param title: The title extracted from front-matter.
+    :param tags: A list of tags (content labels) extracted from front-matter.
     :param text: Text that remains after front-matter and inline properties have been extracted.
     """
 
@@ -74,6 +97,7 @@ class ScannedDocument:
     space_key: Optional[str]
     generated_by: Optional[str]
     title: Optional[str]
+    tags: Optional[list[str]]
     text: str
 
 
@@ -88,30 +112,38 @@ class Scanner:
             text = f.read()
 
         # extract Confluence page ID
-        page_id, text = extract_value(r"<!--\s+confluence-page-id:\s*(\d+)\s+-->", text)
+        page_id, text = extract_value(
+            r"<!--\s+confluence[-_]page[-_]id:\s*(\d+)\s+-->", text
+        )
 
         # extract Confluence space key
         space_key, text = extract_value(
-            r"<!--\s+confluence-space-key:\s*(\S+)\s+-->", text
+            r"<!--\s+confluence[-_]space[-_]key:\s*(\S+)\s+-->", text
         )
 
         # extract 'generated-by' tag text
-        generated_by, text = extract_value(r"<!--\s+generated-by:\s*(.*)\s+-->", text)
+        generated_by, text = extract_value(
+            r"<!--\s+generated[-_]by:\s*(.*)\s+-->", text
+        )
 
         title: Optional[str] = None
+        tags: Optional[list[str]] = None
 
         # extract front-matter
-        properties, text = extract_frontmatter_properties(text)
-        if properties is not None:
-            page_id = page_id or get_string(properties, "confluence-page-id")
-            space_key = space_key or get_string(properties, "confluence-space-key")
-            generated_by = generated_by or get_string(properties, "generated-by")
-            title = get_string(properties, "title")
+        data, text = extract_frontmatter_properties(text)
+        if data is not None:
+            p = _json_to_object(DocumentProperties, data)
+            page_id = page_id or p.confluence_page_id or p.page_id
+            space_key = space_key or p.confluence_space_key or p.space_key
+            generated_by = generated_by or p.generated_by
+            title = p.title
+            tags = p.tags
 
         return ScannedDocument(
             page_id=page_id,
             space_key=space_key,
             generated_by=generated_by,
             title=title,
+            tags=tags,
             text=text,
         )

markdown_to_confluence-0.3.5.dist-info/RECORD

@@ -1,23 +0,0 @@
-markdown_to_confluence-0.3.5.dist-info/licenses/LICENSE,sha256=Pv43so2bPfmKhmsrmXFyAvS7M30-1i1tzjz6-dfhyOo,1077
-md2conf/__init__.py,sha256=Uaqb3maQScpYs3FiH8kuM6pUh5JzE4Vy52MgU9pvMTw,402
-md2conf/__main__.py,sha256=bFcfmSnTWeuhmDm7bJ3jJabZ2S8W9biuAP6_R-Cc9As,8034
-md2conf/api.py,sha256=VxrAJ4yCsdGFVAEQQWw5aONwsMz0b6KvN4EMLXCKOwE,26905
-md2conf/application.py,sha256=SIM4yLHaLnvG7wRJLbRvptrkc0q4JMuAhDnanqsuYzA,6697
-md2conf/converter.py,sha256=ASXhs7g79dOU4x1QhfvKL8mtwth508GTGcb3AUHigC4,37286
-md2conf/emoji.py,sha256=48QJtOD0F3Be1laYLvAOwe0GxrJS-vcfjtCdiBsNcAc,1960
-md2conf/entities.dtd,sha256=M6NzqL5N7dPs_eUA_6sDsiSLzDaAacrx9LdttiufvYU,30215
-md2conf/local.py,sha256=998bBRpDAOywA-L0KD4_VyuL2Xftflv0ler-uNPQZn4,3866
-md2conf/matcher.py,sha256=y5WEZNklTpUoJtMJlulTvfhl_v-UMU6wySJAKit91ig,4940
-md2conf/mermaid.py,sha256=ZETocFDKi_fSYyVR1pJ7fo207YYFSuT44MSYFQ8-cZ0,2562
-md2conf/metadata.py,sha256=Xozg2PjJnis7VQYQT_edIvTb8u0cs_ZizPOAxc1N8vg,1003
-md2conf/processor.py,sha256=jSLFy8hqZJXf3b79jp31Fn9-cm4j9xq4HDChp9pyhP0,6706
-md2conf/properties.py,sha256=TOCXLdTfYkKjRwZaMgvXw0mNCI4opEUwpBXro2Kv2B4,2467
-md2conf/puppeteer-config.json,sha256=-dMTAN_7kNTGbDlfXzApl0KJpAWna9YKZdwMKbpOb60,159
-md2conf/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-md2conf/scanner.py,sha256=iF8NCQAFO6Yut5aAQr7uxfWzVMMt9j3T5ADoVVSJWKQ,3543
-markdown_to_confluence-0.3.5.dist-info/METADATA,sha256=NiXwBXtQ5WhHce_JX7TBUSefQSR5jk5fERe46BL4vwE,18462
-markdown_to_confluence-0.3.5.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-markdown_to_confluence-0.3.5.dist-info/entry_points.txt,sha256=F1zxa1wtEObtbHS-qp46330WVFLHdMnV2wQ-ZorRmX0,50
-markdown_to_confluence-0.3.5.dist-info/top_level.txt,sha256=_FJfl_kHrHNidyjUOuS01ngu_jDsfc-ZjSocNRJnTzU,8
-markdown_to_confluence-0.3.5.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
-markdown_to_confluence-0.3.5.dist-info/RECORD,,