markdown-to-confluence 0.2.2__py3-none-any.whl → 0.2.3__py3-none-any.whl

{markdown_to_confluence-0.2.2.dist-info → markdown_to_confluence-0.2.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: markdown-to-confluence
-Version: 0.2.2
+Version: 0.2.3
 Summary: Publish Markdown files to Confluence wiki
 Home-page: https://github.com/hunyadi/md2conf
 Author: Levente Hunyadi
@@ -208,13 +208,13 @@ You can run the Docker container via `docker run` or via `Dockerfile`. Either ca
 With `docker run`, you can pass Confluence domain, user, API and space key directly to `docker run`:
 
 ```sh
-docker run --rm --name md2conf -v $(pwd):/data leventehunyadi/md2conf -d instructure.atlassian.net -u levente.hunyadi@instructure.com -a 0123456789abcdef -s DAP ./
+docker run --rm --name md2conf -v $(pwd):/data leventehunyadi/md2conf:latest -d instructure.atlassian.net -u levente.hunyadi@instructure.com -a 0123456789abcdef -s DAP ./
 ```
 
 Alternatively, you can use a separate file `.env` to pass these parameters as environment variables:
 
 ```sh
-docker run --rm --env-file .env --name md2conf -v $(pwd):/data leventehunyadi/md2conf ./
+docker run --rm --env-file .env --name md2conf -v $(pwd):/data leventehunyadi/md2conf:latest ./
 ```
 
 In each case, `-v $(pwd):/data` maps the current directory to Docker container's `WORKDIR` such *md2conf* can scan files and directories in the local file system.

markdown_to_confluence-0.2.3.dist-info/RECORD

@@ -0,0 +1,21 @@
+md2conf/__init__.py,sha256=ypRfZF5ef0nZONGa1E9S2htodyslp3uPDgRUhUD8St4,402
+md2conf/__main__.py,sha256=_qUspNQmQdhpH4Myh9vXDcauPyUx_FyEzNtaW_c8ytY,6601
+md2conf/api.py,sha256=bP3Kp4PsGQrPyQMOs-MwE2Znl1ewuKNslMCv7AtXIT0,16366
+md2conf/application.py,sha256=GUMPZUe_jZTBszKDyh4y-jeOp83VKCR3b_EHmzcL5Qs,7778
+md2conf/converter.py,sha256=F75UtnCR3vxAE1W8JxZ5wmfzgtJLTeQvDN2jH49fNXU,33466
+md2conf/emoji.py,sha256=2vMZlLD4m2X6MB-Fjv_GDzEUelb_sg4UBtF463d_p90,1792
+md2conf/entities.dtd,sha256=M6NzqL5N7dPs_eUA_6sDsiSLzDaAacrx9LdttiufvYU,30215
+md2conf/matcher.py,sha256=bZMX_GTXuEeKqIPDES8KqAqTBiesKfSH9rwbNFkD25A,3451
+md2conf/mermaid.py,sha256=a7PVcd7kcFBOMw7Z2mOfvWC1JIVR4Q1EkkanLk1SLx0,1981
+md2conf/processor.py,sha256=qnoO7kTPF2y5uUATnqGSkgVP2DJJiR8DwkUqWavE6r4,4036
+md2conf/properties.py,sha256=2l1tW8HmnrEsXN4-Dtby2tYJQTG1MirRpM3H6ykjQ4c,1858
+md2conf/puppeteer-config.json,sha256=-dMTAN_7kNTGbDlfXzApl0KJpAWna9YKZdwMKbpOb60,159
+md2conf/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+md2conf/util.py,sha256=mghtBv5c0vOBHi5CxjBh4LZbjQ0Cu0h_vB30RN4N8Bk,611
+markdown_to_confluence-0.2.3.dist-info/LICENSE,sha256=Pv43so2bPfmKhmsrmXFyAvS7M30-1i1tzjz6-dfhyOo,1077
+markdown_to_confluence-0.2.3.dist-info/METADATA,sha256=Z7ts-W_aUJiau-mnFZIY6RPF5OdX_xCN081FCW4BNa8,11585
+markdown_to_confluence-0.2.3.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
+markdown_to_confluence-0.2.3.dist-info/entry_points.txt,sha256=F1zxa1wtEObtbHS-qp46330WVFLHdMnV2wQ-ZorRmX0,50
+markdown_to_confluence-0.2.3.dist-info/top_level.txt,sha256=_FJfl_kHrHNidyjUOuS01ngu_jDsfc-ZjSocNRJnTzU,8
+markdown_to_confluence-0.2.3.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
+markdown_to_confluence-0.2.3.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__ = "0.2.2"
+__version__ = "0.2.3"
 __author__ = "Levente Hunyadi"
 __copyright__ = "Copyright 2022-2024, Levente Hunyadi"
 __license__ = "MIT"

md2conf/api.py

@@ -2,7 +2,6 @@ import io
 import json
 import logging
 import mimetypes
-import sys
 import typing
 from contextlib import contextmanager
 from dataclasses import dataclass
@@ -15,6 +14,7 @@ import requests
 
 from .converter import ParseError, sanitize_confluence
 from .properties import ConfluenceError, ConfluenceProperties
+from .util import removeprefix
 
 # a JSON type with possible `null` values
 JsonType = Union[
@@ -44,25 +44,6 @@ def build_url(base_url: str, query: Optional[Dict[str, str]] = None) -> str:
     return urlunparse(url_parts)
 
 
-if sys.version_info >= (3, 9):
-
-    def removeprefix(string: str, prefix: str) -> str:
-        "If the string starts with the prefix, return the string without the prefix; otherwise, return the original string."
-
-        return string.removeprefix(prefix)
-
-else:
-
-    def removeprefix(string: str, prefix: str) -> str:
-        "If the string starts with the prefix, return the string without the prefix; otherwise, return the original string."
-
-        if string.startswith(prefix):
-            prefix_len = len(prefix)
-            return string[prefix_len:]
-        else:
-            return string
-
-
 LOGGER = logging.getLogger(__name__)
 
 

md2conf/application.py

@@ -95,7 +95,7 @@ class Application:
         files: List[Path] = []
         directories: List[Path] = []
         for entry in os.scandir(local_dir):
-            if matcher.is_excluded(entry.name):
+            if matcher.is_excluded(entry.name, entry.is_dir()):
                 continue
 
             if entry.is_file():

md2conf/converter.py

@@ -7,9 +7,10 @@ import os.path
 import re
 import sys
 import uuid
+import xml.etree.ElementTree
 from dataclasses import dataclass
 from pathlib import Path
-from typing import Dict, List, Literal, Optional, Tuple
+from typing import Any, Dict, List, Literal, Optional, Tuple
 from urllib.parse import ParseResult, urlparse, urlunparse
 
 import lxml.etree as ET
@@ -55,6 +56,27 @@ def is_relative_url(url: str) -> bool:
     return not bool(urlparts.scheme) and not bool(urlparts.netloc)
 
 
+def emoji_generator(
+    index: str,
+    shortname: str,
+    alias: Optional[str],
+    uc: Optional[str],
+    alt: str,
+    title: Optional[str],
+    category: Optional[str],
+    options: Dict[str, Any],
+    md: markdown.Markdown,
+) -> xml.etree.ElementTree.Element:
+    name = (alias or shortname).strip(":")
+    span = xml.etree.ElementTree.Element("span", {"data-emoji": name})
+    if uc is not None:
+        # convert series of Unicode code point hexadecimal values into characters
+        span.text = "".join(chr(int(item, base=16)) for item in uc.split("-"))
+    else:
+        span.text = alt
+    return span
+
+
 def markdown_to_html(content: str) -> str:
     return markdown.markdown(
         content,
@@ -62,11 +84,17 @@ def markdown_to_html(content: str) -> str:
             "admonition",
             "markdown.extensions.tables",
             "markdown.extensions.fenced_code",
+            "pymdownx.emoji",
             "pymdownx.magiclink",
             "pymdownx.tilde",
             "sane_lists",
             "md_in_html",
         ],
+        extension_configs={
+            "pymdownx.emoji": {
+                "emoji_generator": emoji_generator,
+            }
+        },
     )
 
 
@@ -81,6 +109,7 @@ def _elements_from_strings(dtd_path: Path, items: List[str]) -> ET._Element:
 
     parser = ET.XMLParser(
         remove_blank_text=True,
+        remove_comments=True,
         strip_cdata=False,
         load_dtd=True,
     )
@@ -678,6 +707,23 @@ class ConfluenceStorageFormatConverter(NodeVisitor):
             AC("rich-text-body", {}, *list(elem)),
         )
 
+    def _transform_emoji(self, elem: ET._Element) -> ET._Element:
+        shortname = elem.attrib.get("data-emoji", "")
+        alt = elem.text or ""
+
+        # <ac:emoticon ac:name="wink" ac:emoji-shortname=":wink:" ac:emoji-id="1f609" ac:emoji-fallback="&#128521;"/>
+        # <ac:emoticon ac:name="blue-star" ac:emoji-shortname=":heavy_plus_sign:" ac:emoji-id="2795" ac:emoji-fallback="&#10133;"/>
+        # <ac:emoticon ac:name="blue-star" ac:emoji-shortname=":heavy_minus_sign:" ac:emoji-id="2796" ac:emoji-fallback="&#10134;"/>
+        return AC(
+            "emoticon",
+            {
+                # use "blue-star" as a placeholder name to ensure wiki page loads in timely manner
+                ET.QName(namespaces["ac"], "name"): "blue-star",
+                ET.QName(namespaces["ac"], "emoji-shortname"): f":{shortname}:",
+                ET.QName(namespaces["ac"], "emoji-fallback"): alt,
+            },
+        )
+
     def transform(self, child: ET._Element) -> Optional[ET._Element]:
         # normalize line breaks to regular space in element text
         if child.text:
@@ -764,6 +810,9 @@ class ConfluenceStorageFormatConverter(NodeVisitor):
         elif child.tag == "pre" and len(child) == 1 and child[0].tag == "code":
             return self._transform_block(child[0])
 
+        elif child.tag == "span" and child.attrib.has_key("data-emoji"):
+            return self._transform_emoji(child)
+
         return None
 
 
@@ -963,3 +1012,39 @@ def elements_to_string(root: ET._Element) -> str:
         return m.group(1)
     else:
         raise ValueError("expected: Confluence content")
+
+
+def _content_to_string(dtd_path: Path, content: str) -> str:
+    parser = ET.XMLParser(
+        remove_blank_text=True,
+        remove_comments=True,
+        strip_cdata=False,
+        load_dtd=True,
+    )
+
+    ns_attr_list = "".join(
+        f' xmlns:{key}="{value}"' for key, value in namespaces.items()
+    )
+
+    data = [
+        '<?xml version="1.0"?>',
+        f'<!DOCTYPE ac:confluence PUBLIC "-//Atlassian//Confluence 4 Page//EN" "{dtd_path}">'
+        f"<root{ns_attr_list}>",
+    ]
+    data.append(content)
+    data.append("</root>")
+
+    tree = ET.fromstringlist(data, parser=parser)
+    return ET.tostring(tree, pretty_print=True).decode("utf-8")
+
+
+def content_to_string(content: str) -> str:
+    "Converts a Confluence Storage Format document returned by the API into a readable XML document."
+
+    if sys.version_info >= (3, 9):
+        resource_path = resources.files(__package__).joinpath("entities.dtd")
+        with resources.as_file(resource_path) as dtd_path:
+            return _content_to_string(dtd_path, content)
+    else:
+        with resources.path(__package__, "entities.dtd") as dtd_path:
+            return _content_to_string(dtd_path, content)

md2conf/emoji.py

@@ -0,0 +1,48 @@
+import pathlib
+
+import pymdownx.emoji1_db as emoji_db
+
+
+def generate_source(path: pathlib.Path) -> None:
+    "Generates a source Markdown document for testing emojis."
+
+    emojis = emoji_db.emoji
+
+    with open(path, "w") as f:
+        print("<!-- confluence-page-id: 86918529216 -->", file=f)
+        print("<!-- This file has been generated by a script. -->", file=f)
+        print(file=f)
+        print("## Emoji", file=f)
+        print(file=f)
+        print("| Icon | Emoji code |", file=f)
+        print("| ---- | ---------- |", file=f)
+        for key in emojis.keys():
+            key = key.strip(":")
+            print(f"| :{key}: | `:{key}:` |", file=f)
+
+
+def generate_target(path: pathlib.Path) -> None:
+    "Generates a target Confluence Storage Format (XML) document for testing emojis."
+
+    emojis = emoji_db.emoji
+
+    with open(path, "w") as f:
+        print('<ac:structured-macro ac:name="info" ac:schema-version="1">', file=f)
+        print("<ac:rich-text-body>", file=f)
+        print("<p>This page has been generated with a tool.</p>", file=f)
+        print("</ac:rich-text-body>", file=f)
+        print("</ac:structured-macro>", file=f)
+        print("<h2>Emoji</h2>", file=f)
+        print("<table>", file=f)
+        print("<thead><tr><th>Icon</th><th>Emoji code</th></tr></thead>", file=f)
+        print("<tbody>", file=f)
+        for key, data in emojis.items():
+            key = key.strip(":")
+            unicode = "".join(f"&#x{item};" for item in data["unicode"].split("-"))
+
+            print(
+                f'<tr><td><ac:emoticon ac:name="blue-star" ac:emoji-shortname=":{key}:" ac:emoji-fallback="{unicode}"/></td><td><code>:{key}:</code></td></tr>',
+                file=f,
+            )
+        print("</tbody>", file=f)
+        print("</table>", file=f)

md2conf/matcher.py

@@ -5,6 +5,14 @@ from pathlib import Path
 from typing import Iterable, List, Optional
 
 
+@dataclass
+class Entry:
+    "Represents a file or directory entry."
+
+    name: str
+    is_dir: bool
+
+
 @dataclass
 class MatcherOptions:
     """
@@ -42,13 +50,21 @@ class Matcher:
 
         return self.options.extension is None or name.endswith(self.options.extension)
 
-    def is_excluded(self, name: str) -> bool:
-        "True if the file or directory name matches any of the exclusion patterns."
+    def is_excluded(self, name: str, is_dir: bool) -> bool:
+        """
+        True if the file or directory name matches any of the exclusion patterns.
+
+        :param name: Name to match against the rule-set.
+        :param is_dir: Whether the name identifies a directory.
+        :returns: True if the name matches at least one of the exclusion patterns.
+        """
 
+        # skip hidden files and directories
         if name.startswith("."):
             return True
 
-        if not self.extension_matches(name):
+        # match extension for regular files
+        if not is_dir and not self.extension_matches(name):
             return True
 
         for rule in self.rules:
@@ -57,12 +73,18 @@ class Matcher:
         else:
             return False
 
-    def is_included(self, name: str) -> bool:
-        "True if the file or directory name matches none of the exclusion patterns."
+    def is_included(self, name: str, is_dir: bool) -> bool:
+        """
+        True if the file or directory name matches none of the exclusion patterns.
+
+        :param name: Name to match against the rule-set.
+        :param is_dir: Whether the name identifies a directory.
+        :returns: True if the name doesn't match any of the exclusion patterns.
+        """
 
-        return not self.is_excluded(name)
+        return not self.is_excluded(name, is_dir)
 
-    def filter(self, items: Iterable[str]) -> List[str]:
+    def filter(self, items: Iterable[Entry]) -> List[Entry]:
         """
         Returns only those elements from the input that don't match any of the exclusion rules.
 
@@ -70,9 +92,9 @@ class Matcher:
         :returns: A filtered list of names that didn't match any of the exclusion rules.
         """
 
-        return [item for item in items if self.is_included(item)]
+        return [item for item in items if self.is_included(item.name, item.is_dir)]
 
-    def scandir(self, path: Path) -> List[str]:
+    def scandir(self, path: Path) -> List[Entry]:
         """
         Returns only those entries in a directory whose name doesn't match any of the exclusion rules.
 
@@ -80,4 +102,6 @@ class Matcher:
         :returns: A filtered list of entries whose name didn't match any of the exclusion rules.
         """
 
-        return self.filter(entry.name for entry in os.scandir(path))
+        return self.filter(
+            Entry(entry.name, entry.is_dir()) for entry in os.scandir(path)
+        )

md2conf/processor.py

@@ -75,7 +75,7 @@ class Processor:
         files: List[Path] = []
         directories: List[Path] = []
         for entry in os.scandir(local_dir):
-            if matcher.is_excluded(entry.name):
+            if matcher.is_excluded(entry.name, entry.is_dir()):
                 continue
 
             if entry.is_file():

md2conf/util.py

@@ -0,0 +1,19 @@
+import sys
+
+if sys.version_info >= (3, 9):
+
+    def removeprefix(string: str, prefix: str) -> str:
+        "If the string starts with the prefix, return the string without the prefix; otherwise, return the original string."
+
+        return string.removeprefix(prefix)
+
+else:
+
+    def removeprefix(string: str, prefix: str) -> str:
+        "If the string starts with the prefix, return the string without the prefix; otherwise, return the original string."
+
+        if string.startswith(prefix):
+            prefix_len = len(prefix)
+            return string[prefix_len:]
+        else:
+            return string

markdown_to_confluence-0.2.2.dist-info/RECORD

@@ -1,19 +0,0 @@
-md2conf/__init__.py,sha256=1DSbQlz0zNxil7Lbsh7VjmGvJdtKhOjtd67r2elUSjE,402
-md2conf/__main__.py,sha256=_qUspNQmQdhpH4Myh9vXDcauPyUx_FyEzNtaW_c8ytY,6601
-md2conf/api.py,sha256=UZ7mkeE1d_f_bACj8LC-t6d4EqXFQCufbeVVdi4FsTs,16947
-md2conf/application.py,sha256=mQusGnzu-ssFn9-aC_rGsqsWpDtw8qFJDnPW7cRkXC0,7762
-md2conf/converter.py,sha256=_zFk-H4NZuY2Y58enVGgFNubOJv9EI2u8tS7RQRiD3A,30391
-md2conf/entities.dtd,sha256=M6NzqL5N7dPs_eUA_6sDsiSLzDaAacrx9LdttiufvYU,30215
-md2conf/matcher.py,sha256=SAmXQzQNan05jVcmZ8PEONynj-SEcVrkCHyXvBxEi2Q,2690
-md2conf/mermaid.py,sha256=a7PVcd7kcFBOMw7Z2mOfvWC1JIVR4Q1EkkanLk1SLx0,1981
-md2conf/processor.py,sha256=V_kxpk4da8vzSLx4Zixhf1sEWdVIxKZeJocJvWhOK6Y,4020
-md2conf/properties.py,sha256=2l1tW8HmnrEsXN4-Dtby2tYJQTG1MirRpM3H6ykjQ4c,1858
-md2conf/puppeteer-config.json,sha256=-dMTAN_7kNTGbDlfXzApl0KJpAWna9YKZdwMKbpOb60,159
-md2conf/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-markdown_to_confluence-0.2.2.dist-info/LICENSE,sha256=Pv43so2bPfmKhmsrmXFyAvS7M30-1i1tzjz6-dfhyOo,1077
-markdown_to_confluence-0.2.2.dist-info/METADATA,sha256=a_CQkC2-De5lcIAudWShsx0m1DIAtA6utrsJKcAi20I,11571
-markdown_to_confluence-0.2.2.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
-markdown_to_confluence-0.2.2.dist-info/entry_points.txt,sha256=F1zxa1wtEObtbHS-qp46330WVFLHdMnV2wQ-ZorRmX0,50
-markdown_to_confluence-0.2.2.dist-info/top_level.txt,sha256=_FJfl_kHrHNidyjUOuS01ngu_jDsfc-ZjSocNRJnTzU,8
-markdown_to_confluence-0.2.2.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
-markdown_to_confluence-0.2.2.dist-info/RECORD,,