Handle extra elements and group text together.

eorg/const.py

@@ -1,19 +1,23 @@
-t_BLANK_LINE = '^\s*$'
 METADATA = ['TITLE', 'AUTHOR', 'EMAIL', 'DESCRIPTION', 'KEYWORDS']
 t_META = r"^[#]\+(" + '|'.join(METADATA) +")\:"
+t_BLANK_LINE = '^\s*$'
 t_COMMENT_BEGIN = r"^\#\+BEGIN_COMMENT"
 t_COMMENT_END = r"^\#\+END_COMMENT"
-
+t_EXAMPLE_BEGIN = r"^\#\+BEGIN_EXAMPLE"
+t_EXAMPLE_END = r"^\#\+END_EXAMPLE"
 t_SRC_BEGIN = r"^\#\+BEGIN_SRC\s+"
 t_SRC_END = r"^\#\+END_SRC"
+t_RESULTS_START = r"^\#\+RESULTS:"
+t_RESULTS_END = r"^\:..*"
 
 t_HEADER = r"^\*+"
 
-
 # Start regex, End regex, skip start, skip end, count matches
 TOKENS = {
     "META": (t_META, False, 2, -1, False),
     "COMMENT": (t_COMMENT_BEGIN, t_COMMENT_END, 2, None, False),
+    "EXAMPLE": (t_EXAMPLE_BEGIN, t_EXAMPLE_END, 2, None, False),
     "SRC_BEGIN": (t_SRC_BEGIN, t_SRC_END, 2, None, False),
+    "RESULTS": (t_SRC_BEGIN, t_SRC_END, 2, None, False),
     "HEADER": (t_HEADER, False, 1, None, True),
 }

eorg/generate.py

@@ -15,8 +15,10 @@ builddoc ={
     "BREAK": "br",
     "TEXT": "p",
     "SRC_BEGIN": src,
+    "EXAMPLE": 'pre',
 }
 
+
 def html(doc):
     response = StringIO()
     for item in doc:

eorg/parser.py

@@ -26,11 +26,16 @@ class Document:
         if not idx:
             if default is not None:
                 return default
-            raise ValueError(f'Attribute of {name} does not exist in document')
+            raise ValueError(f"Attribute of {name} does not exist in document")
         if len(idx) == 1:
             return self.doc[idx[0]].value
         return [self.doc[v].value for v in idx]
 
+    def token(self):
+        if self.doc:
+            return self.doc[-1].token
+        return ""
+
     def update(self, value):
         self.doc[-1].value += value
 
@@ -69,16 +74,15 @@ def parseline(text):
         if count is True:
             key += str(level)
         if key == "META":
-            # return block, [match.group(0)[s:e], text[match.end():]]
             return (
                 block,
                 Token(token=match.group(0)[s:e], value=text[match.end() :]),
             )
         return block, Token(token=key, value=text[match.end() :])
     text = text.strip()
-    if text == '':
-        return False, Token(token='BREAK', value=text)
-    return '^\s*$', Token(token='TEXT', value=text + ' ')
+    if text == "":
+        return False, Token(token="BREAK", value=text)
+    return False, Token(token="TEXT", value=text + " ")
 
 
 def parse(stream):
@@ -95,5 +99,8 @@ def parse(stream):
         result = parseline(line)
         if result:
             block = result[0]
+            if doc.token() == "TEXT" and result[1].token == "TEXT":
+                doc.update(result[1].value)
+                continue
             doc.append(result[1])
     return doc

examples/raw/output.py

@@ -6,5 +6,6 @@ from eorg.parser import parse
 with open(os.path.abspath("../../tests/fixtures/test.org"), "r") as fp:
     doc = parse(fp)
     print(doc.title)
-    for item in doc.body():
+    print(doc.keywords)
+    for item in doc:
         print(item)

tests/fixtures/test.org

@@ -1,6 +1,8 @@
 #+TITLE:     Emacs org-mode examples
 #+AUTHOR:    Eric H. Neilsen, Jr.
 #+EMAIL:     neilsen@fnal.gov
+#+DATE: jkkj
+#+KEYWORDS: emacs, orgmode, tests
 #+DESCRIPTION: Test DESCRIPTION
 #+KEYWORDS: key1, key2
 

tests/test_documents.py

@@ -6,4 +6,12 @@ from eorg.parser import parse
 def test_basic():
     with open(os.path.abspath("./tests/fixtures/test.org"), "r") as fp:
         doc = parse(fp)
-        assert len(doc) == 14
+        assert doc.title != ''
+        assert doc.author != ''
+        assert len(doc) == 20
+
+
+def test_body():
+    with open(os.path.abspath("./tests/fixtures/test.org"), "r") as fp:
+        doc = parse(fp)
+        assert len([i for i in doc.body()]) > 0