Major development update.

* Updated LICENSE, READMES/METADATA.md and TODO.md
* Added example blog to examples/
* Added preliminary Pygments support for embedding code in pages.
* Add preliminary Wordpress dump importer
* Expansions to template_tools and metadata to support Blog use case.

pixywerk2/__main__.py

@@ -17,8 +17,8 @@ from typing import Dict, List, cast
 from .processchain import ProcessorChains
 from .processors.processors import PassthroughException
 from .metadata import MetaTree
-from .template_tools import file_list, file_name, file_content, file_metadata, time_iso8601
-
+from .template_tools import file_list, file_name, file_content, file_metadata, time_iso8601, file_raw
+from .pygments import pygments_get_css, pygments_markup_contents_html
 
 logger = logging.getLogger()
 
@@ -79,18 +79,22 @@ def main() -> int:
         "summary": "",
         "description": "",
         "author": "",
-        "author_email": ""
+        "author_email": "",
     }
     meta_tree = MetaTree(args.root, default_metadata)
     file_list_cache = cast(Dict, {})
     file_cont_cache = cast(Dict, {})
     file_name_cache = cast(Dict, {})
+    file_raw_cache = cast(Dict, {})
     default_metadata["globals"] = {
         "get_file_list": file_list(args.root, file_list_cache),
         "get_file_name": file_name(args.root, meta_tree, process_chains, file_name_cache),
         "get_file_content": file_content(args.root, meta_tree, process_chains, file_cont_cache),
+        "get_raw": file_raw(args.root, file_raw_cache),
         "get_file_metadata": file_metadata(meta_tree),
         "get_time_iso8601": time_iso8601("UTC"),
+        "pygments_get_css": pygments_get_css,
+        "pygments_markup_contents_html": pygments_markup_contents_html,
     }
 
     for root, _, files in os.walk(args.root):

pixywerk2/metadata.py

@@ -1,5 +1,6 @@
 """Constructs a tree-like object containing the metadata for a given path, and caches said metadata."""
 
+import fnmatch
 import logging
 import mimetypes
 import os
@@ -108,11 +109,15 @@ m        load .meta (JSON formatted dictionary) for that level, and
         # iterate path components from root to target path
         comps = [self._root] + rel_path.split("/")
         fullpath = ""
+        ospath = os.path.join(self._root, rel_path)
         for pth in comps:
             fullpath = os.path.join(fullpath, pth)
             st = os.stat(fullpath)
 
-            cachekey = fullpath + ".meta"
+            if os.path.isdir(fullpath):
+                cachekey = os.path.join(fullpath, ".meta")
+            else:
+                cachekey = fullpath + ".meta"
             meta = cast(Dict, {})
             try:
                 st_meta = os.stat(cachekey)
@@ -126,16 +131,20 @@ m        load .meta (JSON formatted dictionary) for that level, and
                 meta = jstyleson.load(open(cachekey, "r"))
                 self._cache.put(cachekey, meta, st_meta.st_mtime)
 
+            if fullpath == ospath and "wildcard_metadata" in metablob:
+                for wild in metablob["wildcard_metadata"]:
+                    if fnmatch.fnmatch(pth, wild[0]):
+                        metablob.update(wild[1])
+
             metablob.update(meta)
 
         # return final dict
         metablob["dir"], metablob["file_name"] = os.path.split(rel_path)
         metablob["file_path"] = rel_path
-        metablob["uuid"] = uuid.uuid3(
-            uuid.NAMESPACE_OID, metablob["uuid-oid-root"] + os.path.join(self._root, rel_path)
-        )
+        metablob["relpath"] = os.path.relpath("/", "/" + metablob["dir"])
+        metablob["uuid"] = uuid.uuid3(uuid.NAMESPACE_OID, metablob["uuid-oid-root"] + ospath)
         metablob["os-path"], _ = os.path.split(fullpath)
-        metablob["guessed-type"] = guess_mime(os.path.join(self._root, rel_path))
+        metablob["guessed-type"] = guess_mime(ospath)
         if "mime-type" not in metablob:
             metablob["mime-type"] = metablob["guessed-type"]
         metablob["stat"] = {}

pixywerk2/pygments.py

@@ -0,0 +1,36 @@
+"""Map Pygments into the Template API for inclusion in outputs."""
+from typing import Optional
+
+import pygments
+import pygments.formatters
+import pygments.lexers
+import pygments.util
+import pygments.styles
+
+
+
+def pygments_markup_contents_html(input_text: str, file_type: str, style: Optional[str]=None) -> str:
+    """Format input string with Pygments and return HTML."""
+
+    if style is None:
+        style = 'default'
+    style = pygments.styles.get_style_by_name(style)
+    formatter = pygments.formatters.get_formatter_by_name('html', style=style)
+    try:
+        lexer = pygments.lexers.get_lexer_for_filename(file_type)
+    except pygments.util.ClassNotFound:
+        try:
+            lexer = pygments.lexers.get_lexer_by_name(file_type)
+        except pygments.util.ClassNotFound:
+            lexer = pygments.lexers.get_lexer_by_mimetype(file_type)
+
+    return pygments.highlight(input_text, lexer, formatter)
+
+def pygments_get_css(style: Optional[str]=None) -> str:
+    """Return the CSS styles associated with a particular style definition."""
+
+    if style is None:
+        style = 'default'
+    style = pygments.styles.get_style_by_name(style)
+    formatter = pygments.formatters.get_formatter_by_name('html', style=style)
+    return formatter.get_style_defs()

pixywerk2/template_tools.py

@@ -51,6 +51,14 @@ def file_name(root: str, metatree: MetaTree, processor_chains: ProcessorChains,
 
     return get_file_name
 
+def file_raw(root: str, contcache: Dict) -> Callable:
+    def get_raw(file_name: str) -> str:
+        if file_name in contcache:
+            return contcache[file_name]
+        with open(os.path.join(root, file_name), 'r', encoding="utf-8") as f:
+            return f.read()
+
+    return get_raw
 
 def file_content(root: str, metatree: MetaTree, processor_chains: ProcessorChains, contcache: Dict) -> Callable:
     def get_file_content(file_name: str) -> Iterable:
@@ -59,7 +67,7 @@ def file_content(root: str, metatree: MetaTree, processor_chains: ProcessorChain
         metadata = metatree.get_metadata(file_name)
         chain = processor_chains.get_chain_for_filename(os.path.join(root, file_name), ctx=metadata)
         contcache[file_name] = chain.output
-        return chain.output
+        return unicode(chain.output)
 
     return get_file_content