Merge pull request strictdoc-project#1902 from haxtibal/tdmg/consiste…

…nt_uid

Extend UID regex and use it in SDocNode

strictdoc/backend/sdoc/grammar/grammar.py

@@ -1,8 +1,9 @@
-REGEX_UID = r"([A-Za-z0-9]+[A-Za-z0-9_\-]*)"
+REGEX_UID = r"([\w]+[\w\-. ]*)"
 
 NEGATIVE_MULTILINE_STRING_START = "(?!>>>\n)"
 NEGATIVE_MULTILINE_STRING_END = "(?!^<<<)"
 NEGATIVE_RELATIONS = "(?!^RELATIONS)"
+NEGATIVE_UID = "(?!^UID)"
 NEGATIVE_FREETEXT_END = "(?!^\\[\\/FREETEXT\\]\n)"
 NEGATIVE_INLINE_LINK_START = rf"(?!\[LINK: {REGEX_UID})"
 NEGATIVE_ANCHOR_START = rf"(?!^\[ANCHOR: {REGEX_UID})"
@@ -44,7 +45,7 @@
 ;
 
 FieldName[noskipws]:
-  /{NEGATIVE_RELATIONS}[A-Z]+[A-Z_]*/
+  /{NEGATIVE_UID}{NEGATIVE_RELATIONS}[A-Z]+[A-Z_]*/
 ;
 """
 
@@ -188,6 +189,8 @@
 
 SDocNodeField[noskipws]:
   (
+    field_name = 'UID' ': ' parts+=/{REGEX_UID}/ '\n'
+    |
     field_name = FieldName ':'
     (
         (' ' parts+=SingleLineTextPart '\n')

tests/unit/strictdoc/backend/sdoc/test_dsl_passthrough.py

@@ -193,6 +193,33 @@ def test_021_section_and_document_mid():
     assert input_sdoc == output
 
 
+def test_022_requirement_uid_and_link():
+    input_sdoc = """
+[DOCUMENT]
+TITLE: Test Doc
+
+[REQUIREMENT]
+UID: With spaces and _ and - and . and non latin 特点
+STATEMENT: >>>
+This is a statement.
+
+[TEXT]
+STATEMENT: >>>
+[LINK: With spaces and _ and - and . and non latin 特点]
+<<<
+""".lstrip()
+
+    reader = SDReader()
+
+    document = reader.read(input_sdoc)
+    assert isinstance(document, SDocDocument)
+
+    writer = SDWriter()
+    output = writer.write(document)
+
+    assert input_sdoc == output
+
+
 def test_030_multiline_statement():
     input_sdoc = """
 [DOCUMENT]
@@ -912,7 +939,7 @@ def test_edge_case_02_uid_present_but_empty_with_no_space_character():
         _ = reader.read(input_sdoc)
 
     assert exc_info.type is TextXSyntaxError
-    assert "Expected ' '" == exc_info.value.args[0].decode("utf-8")
+    assert "Expected ': '" == exc_info.value.args[0].decode("utf-8")
 
 
 def test_edge_case_03_uid_present_but_empty_with_space_character():
@@ -931,9 +958,8 @@ def test_edge_case_03_uid_present_but_empty_with_space_character():
         _ = reader.read(input_sdoc)
 
     assert exc_info.type is TextXSyntaxError
-    assert (
-        "Expected '^\\[ANCHOR: ' or '[LINK: ' or '(?!>>>\\n)\\S.*' or '>>>\\n'"
-        in exc_info.value.args[0].decode("utf-8")
+    assert "Expected '([\\w]+[\\w\\-. ]*)'" in exc_info.value.args[0].decode(
+        "utf-8"
     )
 
 
@@ -953,9 +979,8 @@ def test_edge_case_04_uid_present_but_empty_with_two_space_characters():
         _ = reader.read(input_sdoc)
 
     assert exc_info.type is TextXSyntaxError
-    assert (
-        "Expected '^\\[ANCHOR: ' or '[LINK: ' or '(?!>>>\\n)\\S.*' or '>>>\\n'"
-        in exc_info.value.args[0].decode("utf-8")
+    assert "Expected '([\\w]+[\\w\\-. ]*)'" in exc_info.value.args[0].decode(
+        "utf-8"
     )
 
 
@@ -978,9 +1003,8 @@ def test_edge_case_10_empty_multiline_field():
     assert (
         "Expected '^\\[ANCHOR: ' or '[LINK: ' or "
         "'(?ms)(?!^<<<)(?!^\\[\\/FREETEXT\\]\\n)(?!\\[LINK: "
-        "([A-Za-z0-9]+[A-Za-z0-9_\\-]*))(?!^\\[ANCHOR: "
-        "([A-Za-z0-9]+[A-Za-z0-9_\\-]*)).'"
-        in exc_info.value.args[0].decode("utf-8")
+        "([\\w]+[\\w\\-. ]*))(?!^\\[ANCHOR: "
+        "([\\w]+[\\w\\-. ]*)).'" in exc_info.value.args[0].decode("utf-8")
     )