From 9ffd78ca089d34e5f66e65b12a20821fbf8e47ad Mon Sep 17 00:00:00 2001
From: Oly <oly@digitaloctave.com>
Date: Wed, 17 Oct 2018 14:32:17 +0100
Subject: [PATCH] Start of simple html generator

---
 eorg/const.py               |  4 ++--
 eorg/generate.py            | 32 +++++++++++++++++++++++++++++
 eorg/html.py                | 41 +++++++++++++++++++++++++++++++++++++
 eorg/parser.py              |  5 ++++-
 examples/raw/html-output.py | 10 +++++++++
 5 files changed, 89 insertions(+), 3 deletions(-)
 create mode 100644 eorg/generate.py
 create mode 100644 eorg/html.py
 create mode 100644 examples/raw/html-output.py

diff --git a/eorg/const.py b/eorg/const.py
index 8053317..55fa5a5 100755
--- a/eorg/const.py
+++ b/eorg/const.py
@@ -1,11 +1,11 @@
-
+t_BLANK_LINE = '^\s*$'
 METADATA = ['TITLE', 'AUTHOR', 'EMAIL', 'DESCRIPTION', 'KEYWORDS']
 t_META = r"^[#]\+(" + '|'.join(METADATA) +")\:"
 t_COMMENT_BEGIN = r"^\#\+BEGIN_COMMENT"
 t_COMMENT_END = r"^\#\+END_COMMENT"
 
 t_SRC_BEGIN = r"^\#\+BEGIN_SRC\s+"
-t_SRC_END = r"[#]\+END_SRC\s+$"
+t_SRC_END = r"^\#\+END_SRC"
 
 t_HEADER = r"^\*+"
 
diff --git a/eorg/generate.py b/eorg/generate.py
new file mode 100644
index 0000000..d141c5d
--- /dev/null
+++ b/eorg/generate.py
@@ -0,0 +1,32 @@
+from io import StringIO
+from pygments import highlight
+from pygments.lexers import PythonLexer
+from pygments.lexers import get_lexer_by_name
+from pygments.formatters import HtmlFormatter
+
+def src(code):
+    lexer = get_lexer_by_name('lisp')
+    return highlight(code, lexer, HtmlFormatter())
+
+builddoc ={
+    "HEADER1": "h2",
+    "HEADER2": "h3",
+    "HEADER3": "h4",
+    "BREAK": "br",
+    "TEXT": "p",
+    "SRC_BEGIN": src,
+}
+
+def html(doc):
+    response = StringIO()
+    for item in doc:
+        tag = builddoc.get(item.token)
+        if not tag:
+            continue
+        if callable(tag):
+            response.write(tag(item.value))
+            continue
+        else:
+            response.write('<%s>%s<%s/>\n' % (tag, item.value, tag))
+    response.seek(0)
+    return response
diff --git a/eorg/html.py b/eorg/html.py
new file mode 100644
index 0000000..bc621b6
--- /dev/null
+++ b/eorg/html.py
@@ -0,0 +1,41 @@
+from io import StringIO
+from pygments import highlight
+from pygments.lexers import PythonLexer
+from pygments.lexers import get_lexer_by_name
+from pygments.formatters import HtmlFormatter
+
+code = 'print "Hello World"'
+def src(code):
+    lexer = get_lexer_by_name('lisp')
+    return highlight(code, lexer, HtmlFormatter())
+
+
+builddoc ={
+#    "TITLE": "h1",
+#    "EMAIL": "h1",
+#    "AUTHOR": "h1",
+    "HEADER1": "h2",
+    "HEADER2": "h3",
+    "HEADER3": "h4",
+    "BREAK": "br",
+    "TEXT": "p",
+    "SRC_BEGIN": src,
+#    "COMMENT": "pre",
+}
+
+
+
+def generate(doc):
+    response = StringIO()
+    for item in doc:
+        print(item)
+        tag = builddoc.get(item.token)
+        if not tag:
+            continue
+        if callable(tag):
+            response.write(tag(item.value))
+            continue
+        else:
+            response.write('<%s>%s<%s/>\n' % (tag, item.value, tag))
+    response.seek(0)
+    return response
diff --git a/eorg/parser.py b/eorg/parser.py
index 8d7ac86..97d9d6c 100644
--- a/eorg/parser.py
+++ b/eorg/parser.py
@@ -75,7 +75,10 @@ def parseline(text):
                 Token(token=match.group(0)[s:e], value=text[match.end() :]),
             )
         return block, Token(token=key, value=text[match.end() :])
-    return False, Token(token='TEXT', value=text)
+    text = text.strip()
+    if text == '':
+        return False, Token(token='BREAK', value=text)
+    return '^\s*$', Token(token='TEXT', value=text + ' ')
 
 
 def parse(stream):
diff --git a/examples/raw/html-output.py b/examples/raw/html-output.py
new file mode 100644
index 0000000..26f96bb
--- /dev/null
+++ b/examples/raw/html-output.py
@@ -0,0 +1,10 @@
+import os 
+from eorg.parser import parse
+from eorg.html import generate
+
+doc=[]
+with open(os.path.abspath('../../tests/fixtures/test.org'), 'r') as fp:
+    doc = parse(fp)
+
+print('#################')
+print(generate(doc).read())