From 1de9198f0c69152fe6f474185ac351e9500a4ce8 Mon Sep 17 00:00:00 2001
From: Michael Williamson <mike@zwobble.org>
Date: Thu, 24 Nov 2016 21:38:10 +0000
Subject: Implement document matcher parser

---
 mammoth/styles/parser/document_matcher_parser.py | 71 ++++++++++++++++++++++++
 1 file changed, 71 insertions(+)
 create mode 100644 mammoth/styles/parser/document_matcher_parser.py

(limited to 'mammoth/styles/parser/document_matcher_parser.py')

diff --git a/mammoth/styles/parser/document_matcher_parser.py b/mammoth/styles/parser/document_matcher_parser.py
new file mode 100644
index 0000000..77eae3e
--- /dev/null
+++ b/mammoth/styles/parser/document_matcher_parser.py
@@ -0,0 +1,71 @@
+from ... import documents, document_matchers
+from .tokeniser import TokenType
+from .token_parser import try_parse_class_name, parse_string
+
+
+def parse_document_matcher(tokens):
+    if tokens.try_skip(TokenType.IDENTIFIER, "p"):
+        style_id = try_parse_class_name(tokens)
+        style_name = _parse_style_name(tokens)
+        numbering = _parse_numbering(tokens)
+        
+        return document_matchers.paragraph(
+            style_id=style_id,
+            style_name=style_name,
+            numbering=numbering,
+        )
+        
+    elif tokens.try_skip(TokenType.IDENTIFIER, "r"):
+        style_id = try_parse_class_name(tokens)
+        style_name = _parse_style_name(tokens)
+        
+        return document_matchers.run(
+            style_id=style_id,
+            style_name=style_name,
+        )
+    
+    elif tokens.try_skip(TokenType.IDENTIFIER, "b"):
+        return document_matchers.bold
+    
+    elif tokens.try_skip(TokenType.IDENTIFIER, "i"):
+        return document_matchers.italic
+    
+    elif tokens.try_skip(TokenType.IDENTIFIER, "u"):
+        return document_matchers.underline
+    
+    elif tokens.try_skip(TokenType.IDENTIFIER, "strike"):
+        return document_matchers.strikethrough
+    
+    elif tokens.try_skip(TokenType.IDENTIFIER, "comment-reference"):
+        return document_matchers.comment_reference
+
+
+def _parse_style_name(tokens):
+    if tokens.try_skip(TokenType.SYMBOL, "["):
+        tokens.skip(TokenType.IDENTIFIER, "style-name")
+        tokens.skip(TokenType.SYMBOL, "=")
+        name = parse_string(tokens)
+        tokens.skip(TokenType.SYMBOL, "]")
+        return name
+    else:
+        return None
+
+
+def _parse_numbering(tokens):
+    if tokens.try_skip(TokenType.SYMBOL, ":"):
+        is_ordered = _parse_list_type(tokens)
+        tokens.skip(TokenType.SYMBOL, "(")
+        level = int(tokens.next_value(TokenType.INTEGER)) - 1
+        tokens.skip(TokenType.SYMBOL, ")")
+        return documents.numbering_level(level, is_ordered=is_ordered)
+
+
+def _parse_list_type(tokens):
+    list_type = tokens.next_value(TokenType.IDENTIFIER)
+    if list_type == "ordered-list":
+        return True
+    elif list_type == "unordered-list":
+        return False
+    else:
+        pass
+        # TODO: raise
-- 
cgit v1.2.3