Feature to convert markdown file to xml

src/MarkdownFile.py

@@ -1,9 +1,11 @@
 import re
 from src.YamlParser import YamlParser, YAML_METHOD
+from xml.etree.ElementTree import Element, ElementTree, SubElement
 
 class MarkdownFile:
     def __init__(self, fileName, filePath):
         self._regexFindLinks = r'(?<=\[\[).*?(?=(?:\]\]|#|\|))' # Thanks to https://github.com/archelpeg
+        self._regexFindHeaders = r'^\s*(#+)(\s+.*)'
         self.fileName = fileName
         self.path = filePath
         self.tags = self._findTags()
@@ -77,3 +79,47 @@ def _findLinksInCurrentFile(self) -> set:
     def _openFile(self):
         """Open markdown file"""
         return open(self.path, "r", encoding="utf-8")
+
+    def toXML(self):
+        file = self._openFile()
+        lines = file.readlines()
+        file.close()
+
+        # Get the line numbers and header levels of each header
+        section_lines = []
+        section_levels = []
+        section_titles = []
+        for i, line in enumerate(lines):
+            match = re.match(self._regexFindHeaders, line)
+            if match is not None:
+                section_lines.append(i)
+                section_levels.append(len(match.group(1)))
+                section_titles.append(match.group(2).strip())
+
+        root = Element('root', {'level': '0'})
+        parent_map = {}
+
+        current_node = root
+        section_ends = section_lines + [len(lines)]
+        current_node.text = "".join(lines[:section_ends[0]])
+        section_ends = section_ends[1:]
+
+        for section_start, level, title, section_end in zip(section_lines, section_levels, section_titles, section_ends):
+            while int(current_node.get('level')) >= level: 
+                current_node = parent_map[current_node]
+            section_node = SubElement(current_node, 'section', {'level': str(level), 'title': title})
+            parent_map[section_node] = current_node
+            section_node.text = "".join(lines[section_start:section_end])
+
+            current_node = section_node
+
+        return ElementTree(root)
+
+def xmlToMarkdownText(tree: ElementTree):
+    sections = []
+    for node in tree.iter():
+        if node.get('level') == '0':
+            continue
+        sections.append(node.text)
+
+    return ''.join(sections)

test/testVault/xml_markdown_tests/expected_outputs/empty-file.xml

@@ -0,0 +1 @@
+<root level="0" />

test/testVault/xml_markdown_tests/expected_outputs/false-headers.xml

@@ -0,0 +1,14 @@
+<root level="0">Root level text.
+
+<section level="1" title="A good header"># A good header
+
+This header has good text.
+
+#bad header
+
+asdf # another bad header
+
+<section level="2" title="This is okay">    ## This is okay
+
+asdfasdf
+</section></section></root>

test/testVault/xml_markdown_tests/expected_outputs/multi-level-headers.xml

@@ -0,0 +1,22 @@
+<root level="0">Root level text.
+
+<section level="1" title="Header 1"># Header 1
+
+Level 1 text.
+
+<section level="2" title="Header 2">## Header 2
+
+Level 2 text.
+
+<section level="3" title="Header 3">### Header 3
+
+Level 3 text.
+
+<section level="6" title="Header 6">###### Header 6
+
+Level 6 text.
+
+</section></section></section></section><section level="1" title="Section 2"># Section 2
+
+Another section.
+</section></root>

test/testVault/xml_markdown_tests/expected_outputs/no-section.xml

@@ -0,0 +1,2 @@
+<root level="0">This file has no sections.
+</root>

test/testVault/xml_markdown_tests/expected_outputs/single-level-headers.xml

@@ -0,0 +1,14 @@
+<root level="0">root section
+
+<section level="1" title="header 1"># header 1
+
+section 1
+
+</section><section level="1" title="header 2"># header 2
+
+section 2
+
+</section><section level="1" title="header 3"># header 3
+
+section 3
+</section></root>

test/testVault/xml_markdown_tests/markdown_files/false-headers.md

@@ -0,0 +1,13 @@
+Root level text.
+
+# A good header
+
+This header has good text.
+
+#bad header
+
+asdf # another bad header
+
+    ## This is okay
+
+asdfasdf

test/testVault/xml_markdown_tests/markdown_files/multi-level-headers.md

@@ -0,0 +1,21 @@
+Root level text.
+
+# Header 1
+
+Level 1 text.
+
+## Header 2
+
+Level 2 text.
+
+### Header 3
+
+Level 3 text.
+
+###### Header 6
+
+Level 6 text.
+
+# Section 2
+
+Another section.

test/testVault/xml_markdown_tests/markdown_files/no-section.md

@@ -0,0 +1 @@
+This file has no sections.

test/testVault/xml_markdown_tests/markdown_files/single-level-headers.md

@@ -0,0 +1,13 @@
+root section
+
+# header 1
+
+section 1
+
+# header 2
+
+section 2
+
+# header 3
+
+section 3

test/test_Script.py

@@ -1,12 +1,10 @@
-from src.Extractor import Extractor
-from src.MarkdownFile import MarkdownFile
+from src.MarkdownFile import xmlToMarkdownText
 from src.Parser import Parser
-from src.YamlParser import YamlParser
-import os
+from test.xml_helpers import loadXMLSingleLevelHeaders, loadXMLMultiLevelHeaders, loadXMLFalseHeaders, loadXMLEmptyFile, loadXMLNoSection, treesEqual
 
 def testMarkdownsRetrieval():
     parser = Parser('./test/testVault')
-    assert len(parser.mdFiles) == 6
+    assert len(parser.mdFiles) == 11
 
 def testMarkdownTags():
     def nbFilesWithTag(parser, tag):
@@ -22,3 +20,69 @@ def testSubfilesForFile():
     file = set([file for file in parser.mdFiles if file.fileName == 'file1.md'])
     subFiles = parser.findSubFilesForFiles(file)
     assert len(subFiles) == 3
+
+def testXMLBuilderSingleLevelHeaders():
+    parser = Parser('./test/testVault')
+    file = [file for file in parser.mdFiles if file.fileName == 'single-level-headers.md'].pop()
+    assert treesEqual(file.toXML(), loadXMLSingleLevelHeaders())
+
+def testXMLBuilderMultiLevelHeaders():
+    parser = Parser('./test/testVault')
+    file = [file for file in parser.mdFiles if file.fileName == 'multi-level-headers.md'].pop()
+    assert treesEqual(file.toXML(), loadXMLMultiLevelHeaders())
+
+def testXMLBuilderFalseHeaders():
+    parser = Parser('./test/testVault')
+    file = [file for file in parser.mdFiles if file.fileName == 'false-headers.md'].pop()
+    assert treesEqual(file.toXML(), loadXMLFalseHeaders())
+
+def testXMLBuilderEmptyFile():
+    parser = Parser('./test/testVault')
+    file = [file for file in parser.mdFiles if file.fileName == 'empty-file.md'].pop()
+    assert treesEqual(file.toXML(), loadXMLEmptyFile())
+
+def testXMLBuilderNoSectionFile():
+    parser = Parser('./test/testVault')
+    file = [file for file in parser.mdFiles if file.fileName == 'no-section.md'].pop()
+    assert treesEqual(file.toXML(), loadXMLNoSection())
+
+def testXMLWriterSingleLevelHeaders():
+    parser = Parser('./test/testVault')
+    file = [file for file in parser.mdFiles if file.fileName == 'single-level-headers.md'].pop()
+    with open(file.path, 'r') as mdFile:
+        text = mdFile.read()
+
+    xmlToMarkdownText(loadXMLSingleLevelHeaders()) == text
+
+def testXMLWriterMultiLevelHeaders():
+    parser = Parser('./test/testVault')
+    file = [file for file in parser.mdFiles if file.fileName == 'multi-level-headers.md'].pop()
+    with open(file.path, 'r') as mdFile:
+        text = mdFile.read()
+
+    xmlToMarkdownText(loadXMLMultiLevelHeaders()) == text
+
+def testXMLWriterFalseHeaders():
+    parser = Parser('./test/testVault')
+    file = [file for file in parser.mdFiles if file.fileName == 'false-headers.md'].pop()
+    with open(file.path, 'r') as mdFile:
+        text = mdFile.read()
+
+    xmlToMarkdownText(loadXMLFalseHeaders()) == text
+
+def testXMLWriterEmptyFile():
+    parser = Parser('./test/testVault')
+    file = [file for file in parser.mdFiles if file.fileName == 'empty-file.md'].pop()
+    with open(file.path, 'r') as mdFile:
+        text = mdFile.read()
+
+    xmlToMarkdownText(loadXMLEmptyFile()) == text
+
+def testXMLWriterNoSectionFile():
+    parser = Parser('./test/testVault')
+    file = [file for file in parser.mdFiles if file.fileName == 'no-section.md'].pop()
+    with open(file.path, 'r') as mdFile:
+        text = mdFile.read()
+
+    xmlToMarkdownText(loadXMLNoSection()) == text
+

test/xml_helpers.py

@@ -0,0 +1,20 @@
+import xml.etree.ElementTree as ET
+from xml.etree.ElementTree import Element, ElementTree
+
+def treesEqual(t1: ElementTree, t2: ElementTree) -> bool:
+    return ET.canonicalize(ET.tostring(t1.getroot())) == ET.canonicalize(ET.tostring(t2.getroot()))
+
+def loadXMLSingleLevelHeaders(): 
+    return ET.parse('./test/testVault/xml_markdown_tests/expected_outputs/single-level-headers.xml')
+
+def loadXMLMultiLevelHeaders(): 
+    return ET.parse('./test/testVault/xml_markdown_tests/expected_outputs/multi-level-headers.xml')
+
+def loadXMLFalseHeaders(): 
+    return ET.parse('./test/testVault/xml_markdown_tests/expected_outputs/false-headers.xml')
+
+def loadXMLEmptyFile(): 
+    return ET.parse('./test/testVault/xml_markdown_tests/expected_outputs/empty-file.xml')
+
+def loadXMLNoSection(): 
+    return ET.parse('./test/testVault/xml_markdown_tests/expected_outputs/no-section.xml')