Fix up block parsing and better handling of emphasis

eorg/generate.py

@@ -5,77 +5,74 @@ from pygments.lexers import PythonLexer
 from pygments.lexers import get_lexer_by_name
 from pygments.formatters import HtmlFormatter
 
-def src(doc, code, cls='', root=True):
+
+def src(doc, code, cls="", root=True):
     try:
-        lexer = get_lexer_by_name(code.attrs.get('language', 'shell'))
+        lexer = get_lexer_by_name(code.attrs.get("language", "shell"))
     except pygments.util.ClassNotFound as e:
-        lexer = get_lexer_by_name(code.attrs.get('language', 'text'))
+        lexer = get_lexer_by_name(code.attrs.get("language", "text"))
 
     return highlight(code.value, lexer, HtmlFormatter(linenos=True))
 
-def img(doc, item, cls='', root=True):
+
-    caption = doc.previous('CAPTION')
+def img(doc, item, cls="", root=True):
-    text = ''
+    caption = doc.previous("CAPTION")
+    text = ""
     if caption:
         text = f'<p class="center-align">{caption.value}</p>'
     return f'<img{cls} style="margin:auto;" src="{item.value[0]}" alt="{item.value[1]}" />{text}'
 
 
-def parse_text_html(doc, token, cls='', root=True):
+def parse_list_html(doc, token, cls="", root=True):
-    print('test')
-    print(token)
-    # if its the start of a text body wrap html tags
-    # else more complicated so return the tags
-    if isinstance(token.value, str):
-        if root is True:
-            return f'<p{cls}>{token.value}</p>'
-        return f'{token.value}'
-
-
     response = StringIO()
-
+    response.write(f"<p{cls}>")
-    print(token.value)
-    response.write(f'<p{cls}>')
 
     for item in token.value:
-        print(item)
         response.write(handle_token(doc, item, False))
-    response.write(f'</p>')
+    response.write(f"</p>")
-
-    response.seek(0)
-    print(response.read())
     response.seek(0)
     return response.read()
 
+
+def parse_text_html(doc, token, cls="", root=True):
+    # if its the start of a text body wrap html tags
+    # else more complicated so return the tags
+    #if root is True:
+    #    return f"<p{cls}>{token.value}</p>"
+    return f"{token.value}"
+
+
 builddoc = {
     "HEADER1": ("h2", None),
     "HEADER2": ("h3", None),
     "HEADER3": ("h4", None),
     #    "BREAK": "br",
-    "IMG": (img, 'materialboxed center-align responsive-img'),
+    "IMG": (img, "materialboxed center-align responsive-img"),
     "B": ("b", None),
     "U": ("u", None),
     "I": ("i", None),
     "V": ("code", None),
+    "LIST": (parse_list_html, "flow-text"),
     "TEXT": (parse_text_html, "flow-text"),
     "SRC_BEGIN": (src, None),
-    "EXAMPLE": ('blockquote', None),
+    "EXAMPLE": ("blockquote", None),
 }
 
+
 def handle_token(doc, item, root=False):
     response = StringIO()
     match = builddoc.get(item.token)
     if not match:
-        return ''
+        return ""
     tag, cls = match
     if cls:
         cls = f' class="{cls}"'
     else:
-        cls = ''
+        cls = ""
     if callable(tag):
         return tag(doc, item, cls, root=root)
     else:
-        return '<%s%s>%s</%s>\n' % (tag, cls, item.value, tag)
+        return "<%s%s>%s</%s>\n" % (tag, cls, item.value, tag)
 
 
 def html(doc):

eorg/parser.py

@@ -95,8 +95,7 @@ def parse_attrs(text):
 def parsebody(text, rx):
     match = re.search(rx, text)
     if match:
-        return False, ""
+        return False, None
-    else:
     return rx, text + "\n"
 
 def parseline(text):
@@ -119,7 +118,7 @@ def parseline(text):
     text = text.strip()
     if text == "":
         return False, Token(token="BREAK", value=text)
-    return False, Token(token="TEXT", value=text + " ")
+    return False, Token(token="LIST", value=text + " ")
 
 
 def parse_text(txt):
@@ -191,17 +190,16 @@ def parse(stream):
         line = line.strip('\n')
         if block is not False:
             block, token = parsebody(line, block)
-            if token:
+            if block:
-                #block = result[0]
                 doc.update(token)
             continue
         block, token = parseline(line)
         if token:
-            if doc.token() == "TEXT" and token.token == "TEXT":
+            if doc.token() == "LIST" and token.token == "LIST":
                 doc.update(token.value)
                 continue
             doc.append(token)
 
-    for item in doc.filter('TEXT'):
+    for item in doc.filter('LIST'):
         item.value = parse_text(item.value)
     return doc

eorg/version.py

@@ -1,2 +1,2 @@
-__version__ = 0.4
+__version__ = 0.5
 

tests/test_documents.py

@@ -23,4 +23,16 @@ def test_body():
 def test_html_output():
     with open(os.path.abspath("./tests/fixtures/test.org"), "r") as fp:
         doc = parse(fp)
-        assert html(doc).read() == ''
+        htmlbody = html(doc).read()
+        print(htmlbody)
+        assert htmlbody == """<p class="flow-text">#+DATE: jkkj </p><h2> Header 1</h2>
+<h3> Sub Header 1</h3>
+<p class="flow-text">body <code>text</code>
+ over multiple <b>lines</b>
+ </p><h3> Sub Header 2</h3>
+<h2> Header 2</h2>
+<table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre>1</pre></div></td><td class="code"><div class="highlight"><pre><span></span><span class="p">(</span><span class="nv">some</span> <span class="nv">lispy</span> <span class="nv">code</span><span class="p">)</span>
+</pre></div>
+</td></tr></table><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre>1</pre></div></td><td class="code"><div class="highlight"><pre><span></span><span class="p">(</span><span class="nv">test</span> <span class="nv">code</span><span class="p">)</span>
+</pre></div>
+</td></tr></table>"""