Implement document matcher parser

2 files changed, 159 insertions, 0 deletions

diff --git a/tests/styles/parser/document_matcher_parser_tests.py b/tests/styles/parser/document_matcher_parser_tests.py
new file mode 100644
index 0000000..18109ca
--- /dev/null
+++ b/tests/styles/parser/document_matcher_parser_tests.py
@@ -0,0 +1,109 @@
+from nose.tools import istest, assert_equal
+
+from mammoth import documents, document_matchers
+from mammoth.styles.parser.document_matcher_parser import parse_document_matcher
+from mammoth.styles.parser.tokeniser import tokenise
+from mammoth.styles.parser.token_iterator import TokenIterator
+
+
+@istest
+def reads_plain_paragraph():
+    assert_equal(
+        document_matchers.paragraph(),
+        read_document_matcher("p")
+    )
+
+
+@istest
+def reads_paragraph_with_style_id():
+    assert_equal(
+        document_matchers.paragraph(style_id="Heading1"),
+        read_document_matcher("p.Heading1")
+    )
+
+
+@istest
+def reads_paragraph_with_exact_style_name():
+    assert_equal(
+        document_matchers.paragraph(style_name="Heading 1"),
+        read_document_matcher("p[style-name='Heading 1']")
+    )
+
+
+@istest
+def reads_paragraph_ordered_list():
+    assert_equal(
+        document_matchers.paragraph(numbering=documents.numbering_level(1, is_ordered=True)),
+        read_document_matcher("p:ordered-list(2)")
+    )
+
+
+@istest
+def reads_paragraph_unordered_list():
+    assert_equal(
+        document_matchers.paragraph(numbering=documents.numbering_level(1, is_ordered=False)),
+        read_document_matcher("p:unordered-list(2)")
+    )
+
+
+@istest
+def reads_plain_run():
+    assert_equal(
+        document_matchers.run(),
+        read_document_matcher("r")
+    )
+
+
+@istest
+def reads_run_with_style_id():
+    assert_equal(
+        document_matchers.run(style_id="Emphasis"),
+        read_document_matcher("r.Emphasis")
+    )
+
+
+@istest
+def reads_run_with_style_name():
+    assert_equal(
+        document_matchers.run(style_name="Emphasis"),
+        read_document_matcher("r[style-name='Emphasis']")
+    )
+
+@istest
+def reads_bold():
+    assert_equal(
+        document_matchers.bold,
+        read_document_matcher("b")
+    )
+
+@istest
+def reads_italic():
+    assert_equal(
+        document_matchers.italic,
+        read_document_matcher("i")
+    )
+
+@istest
+def reads_underline():
+    assert_equal(
+        document_matchers.underline,
+        read_document_matcher("u")
+    )
+
+@istest
+def reads_strikethrough():
+    assert_equal(
+        document_matchers.strikethrough,
+        read_document_matcher("strike")
+    )
+
+@istest
+def reads_comment_reference():
+    assert_equal(
+        document_matchers.comment_reference,
+        read_document_matcher("comment-reference")
+    )
+
+
+def read_document_matcher(string):
+    return parse_document_matcher(TokenIterator(tokenise(string)))
diff --git a/tests/styles/parser/token_parser_tests.py b/tests/styles/parser/token_parser_tests.py
new file mode 100644
index 0000000..0e278c7
--- /dev/null
+++ b/tests/styles/parser/token_parser_tests.py
@@ -0,0 +1,50 @@
+from nose.tools import istest, assert_equal
+
+from mammoth.styles.parser.tokeniser import Token, TokenType
+from mammoth.styles.parser.token_parser import decode_escape_sequences, parse_identifier, parse_string
+from mammoth.styles.parser.token_iterator import TokenIterator
+
+
+@istest
+def escape_sequences_in_identifiers_are_decoded():
+    assert_equal(
+        ":",
+        parse_identifier(TokenIterator([
+            Token(0, TokenType.IDENTIFIER, r"\:"),
+        ])),
+    )
+
+
+@istest
+def escape_sequences_in_strings_are_decoded():
+    assert_equal(
+        "\n",
+        parse_string(TokenIterator([
+            Token(0, TokenType.STRING, r"'\n'"),
+        ])),
+    )
+
+
+@istest
+def line_feeds_are_decoded():
+    assert_equal("\n", decode_escape_sequences(r"\n"))
+
+
+@istest
+def carriage_returns_are_decoded():
+    assert_equal("\r", decode_escape_sequences(r"\r"))
+
+
+@istest
+def tabs_are_decoded():
+    assert_equal("\t", decode_escape_sequences(r"\t"))
+
+
+@istest
+def backslashes_are_decoded():
+    assert_equal("\\", decode_escape_sequences(r"\\"))
+
+
+@istest
+def colons_are_decoded():
+    assert_equal(":", decode_escape_sequences(r"\:"))