initial commit

1 files changed, 159 insertions, 0 deletions

diff --git a/panfry/document.py b/panfry/document.py
new file mode 100755
index 0000000..42ef959
--- /dev/null
+++ b/panfry/document.py
@@ -0,0 +1,159 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+import os
+import re
+import pandoc
+from tempfile import NamedTemporaryFile
+from panfry.util import *
+
+
+class Document:
+
+    def __init__(self, path):
+        self.src_path = path
+        self.meta = self.get_meta(path)
+        self.pages = self.get_pages(path)
+
+    css_file = 'css/style.css'
+    workdir = 'stdocs-work'
+
+    def get_pages(self, path):
+        pages = []
+        filelist = get_lines(self.meta['TOC'])
+        for filename in filelist:
+            source = read_file(os.path.join(path, filename))
+            if source:
+                pages.append(Page(filename, source))
+            else:
+                print("WARNING: Page: %s not found or is empty." % filename)
+
+        return pages
+
+    def get_meta(self, path):
+        metafiles = ['TOC', 'HEADER']
+        meta = {}
+        for filename in metafiles:
+            source = read_file(os.path.join(path, filename))
+            if source:
+                meta[filename] = source
+            else:
+                print("!E: %s not found or is empty. Aborting..." % filename)
+                exit(1)
+
+        return meta
+
+    def set_templater(self, templater):
+        self.templater = templater
+
+    def next_page(self, page):
+        try:
+            idx = self.pages.index(page)
+        except:
+            return ''
+        if idx >= len(self.pages) - 1:
+            return ''
+        return self.pages[idx+1]
+
+    def prev_page(self, page):
+        try:
+            idx = self.pages.index(page)
+        except:
+            return ''
+        if idx == 0:
+            return ''
+        return self.pages[idx-1]
+
+    @property
+    def toc_links(self):
+        '''
+        Returns a list of dictionaries. Each dictionary element contains
+        a page title and the html file name.
+        '''
+        links = []
+        for page in self.pages:
+            title, level = page.title
+            links.append(dict(link=unicode(page.htmlfile, "utf8"),
+                              text=unicode(title, "utf8"),
+                              level=level,
+                              ))
+
+        return links
+
+    @property
+    def pdf_filename(self):
+        header = self.meta['HEADER']
+        m = re.match('(^%)(.*\n.*)(%*)', header)
+        if m:
+            title = m.group(2).strip()
+            title = re.sub(r'\s+', ' ', title)
+            title = re.sub(r'[\n ]', '_', title)
+            title = re.sub(r'[:,]', '-', title)
+            title = re.sub(r'_+', '_', title)
+            title = re.sub(r'-_', '-', title)
+            title = re.sub(r'-+', '-', title)
+        else:
+            title = os.path.split(self.src_path)[1]
+
+        return title + '.pdf'
+
+    def publish_pdf(self, pub_path):
+        pdf_path = os.path.join(pub_path, self.pdf_filename)
+        src = self.meta['HEADER']
+        for page in self.pages:
+            src += '\n%s' % page.source
+
+        doc = pandoc.Document()
+        doc.markdown = src
+
+        pandoc.set_cwd(os.path.abspath(self.src_path))
+        doc.to_file(pdf_path)
+        pandoc.set_cwd(None)
+
+        return self.pdf_filename
+
+    def publish_css(self, pub_path):
+        src = os.path.join(self.src_path, 'css')
+        dst = os.path.join(pub_path, 'css')
+        if os.path.isdir(src):
+            copy(src, dst)
+
+    def publish_images(self, pub_path):
+        src_path = self.src_path
+        if os.path.exists(os.path.join(src_path, 'images/html')):
+            src = os.path.join(src_path, 'images/html')
+        else:
+            src = os.path.join(src_path, 'images')
+
+        dst = os.path.join(pub_path, 'images')
+        if os.path.exists(src):
+            copy(src, dst)
+
+    def publish_html(self, pub_path):
+        pandoc.set_cwd(None)
+        for page in self.pages:
+            print("generating %s..." % page.htmlfile)
+            template_file = NamedTemporaryFile(mode='w',
+                                               suffix='pf.template',
+                                               delete=False)
+            template = self.templater.page_template(self, page)
+            template_file.write(template)
+            template_file.close()
+            doc = pandoc.Document()
+            doc.add_argument('toc')
+            doc.add_argument('template=%s' % template_file.name)
+            doc.add_argument('css=%s' % self.css_file)
+            doc.markdown = page.source
+            content = doc.html
+            write_file(os.path.join(pub_path, page.htmlfile),
+                       unicode(content, 'utf-8'))
+
+        # If there is not explicit index.html, then link 'index.html'
+        # to the toplevel page.
+        if not 'index.md' in self.pages:
+            src = os.path.join(self.pages[0].htmlfile)
+            ref = os.path.join(pub_path, 'index.html')
+            os.symlink(src, ref)
+
+        ###### Copy any images to publish directory
+        self.publish_css(pub_path)
+        self.publish_images(pub_path)