From 95cb13208dac4dcc32f4d32c987da6834cb6ba75 Mon Sep 17 00:00:00 2001
From: David Luevano Alvarado <david@luevano.xyz>
Date: Mon, 28 Aug 2023 19:01:52 -0600
Subject: refactor: simplify parser and page code, remove unnecessary debu logs
---
src/pyssg/builder.py | 23 ++++++---------
src/pyssg/md_parser.py | 26 +++++-----------
src/pyssg/page.py | 77 +++++++++++-------------------------------------
src/pyssg/plt/index.html | 8 ++---
src/pyssg/plt/page.html | 6 ++--
src/pyssg/plt/tag.html | 8 ++---
6 files changed, 46 insertions(+), 102 deletions(-)
diff --git a/src/pyssg/builder.py b/src/pyssg/builder.py
index dc7bdda..1eec345 100644
--- a/src/pyssg/builder.py
+++ b/src/pyssg/builder.py
@@ -54,7 +54,7 @@ class Builder:
# files and pages are synoyms
self.all_files: list[Page]
- self.all_tags: list[tuple[str, str]]
+ self.all_tags: list[str]
self.common_vars: dict
def build(self) -> None:
@@ -100,12 +100,12 @@ class Builder:
self.__render_pages(self.dir_cfg['plt'])
if self.dir_cfg['tags']:
- log.debug('rendering tags for dir "%s"', self.dir_cfg['dir'])
- create_dir(os.path.join(self.dir_cfg['dst'], 'tag'), True)
+ create_dir(os.path.join(self.dir_cfg['dst'], 'tags'), True)
if isinstance(self.dir_cfg['tags'], str):
self.__render_tags(self.dir_cfg['tags'])
else:
self.__render_tags('tag.html')
+ log.debug('rendered tags for dir "%s"', self.dir_cfg['dir'])
default_plts: dict[str, str] = {'index': 'index.html',
'rss': 'rss.xml',
@@ -158,32 +158,27 @@ class Builder:
tag_vars: dict = deepcopy(self.common_vars)
tag_pages: list[Page]
for t in self.all_tags:
- log.debug('rendering tag "%s"', t[0])
# clean tag_pages
tag_pages = []
- log.debug('adding all pages that contain current tag')
for p in self.all_files:
- if p.tags is not None and t[0] in list(map(itemgetter(0),
- p.tags)):
- log.debug('adding page "%s" as it contains tag "%s"',
- p.name, t[0])
+ if p.tags is not None and t in p.tags:
tag_pages.append(p)
- log.debug('adding tag and tag_pages to exposed vars for jinja')
+ log.debug('added page "%s" to tag "%s"', p.name, t)
tag_vars['tag'] = t
tag_vars['tag_pages'] = tag_pages
- t_fname: str = f'tag/@{t[0]}.html'
+ t_fname: str = f'tags/{t}.html'
# actually render tag page
self.__render_template(template_name, t_fname, **tag_vars)
+ log.debug('rendered tag "%s"', t)
def __render_template(self, template_name: str,
file_name: str,
**template_vars) -> None:
- log.debug('rendering html "%s" with template "%s"',
- file_name, template_name)
template: Template = self.env.get_template(template_name)
content: str = template.render(**template_vars)
dst_path: str = os.path.join(self.dir_cfg['dst'], file_name)
- log.debug('writing html file to path "%s"', dst_path)
with open(dst_path, 'w') as f:
f.write(content)
+ log.debug('wrote html at "%s"', dst_path)
+
diff --git a/src/pyssg/md_parser.py b/src/pyssg/md_parser.py
index 7056a5b..0c0dd5b 100644
--- a/src/pyssg/md_parser.py
+++ b/src/pyssg/md_parser.py
@@ -75,7 +75,7 @@ class MDParser:
self.md: Markdown = get_md_obj(self.pymdvar_vars, self.pymdvar_enable_env)
self.all_files: list[Page] = []
- self.all_tags: list[tuple[str, str]] = []
+ self.all_tags: list[str] = []
def parse_files(self) -> None:
for i, f in enumerate(self.files):
@@ -98,7 +98,6 @@ class MDParser:
else:
entry = oentry
- log.debug('parsing md into html')
# ignoring md.Meta type as it is not yet defined
# (because it is from an extension)
page: Page = Page(f,
@@ -108,35 +107,26 @@ class MDParser:
self.md.toc, # type: ignore
self.md.toc_tokens, # type: ignore
self.md.Meta, # type: ignore
- self.config,
- self.dir_config)
+ self.config)
page.parse_metadata()
-
- log.debug('adding to file list')
self.all_files.append(page)
if self.dir_config['tags']:
- if page.tags is None:
- self.db.update_tags(f)
- else:
- tags: tuple = tuple(set(map(itemgetter(0), page.tags)))
- if tags != entry[4]:
- self.db.update_tags(f, tags)
+ if entry[4] is not None:
+ if set(page.tags) != set(entry[4]):
+ self.db.update_tags(f, page.tags)
- log.debug('add all tags to tag list')
for t in page.tags:
- if t[0] not in list(map(itemgetter(0), self.all_tags)):
+ if t not in self.all_tags:
self.all_tags.append(t)
- log.debug('added tag "%s"', t[0])
+ log.debug('added tag "%s" to all tags', t)
- log.debug('sorting all lists for consistency')
self.all_files.sort(reverse=True)
- self.all_tags.sort(key=itemgetter(0))
+ self.all_tags.sort()
pages_amount: int = len(self.all_files)
# note that prev and next are switched because of the
# reverse ordering of all_pages
- log.debug('update next and prev attributes')
for i, p in enumerate(self.all_files):
if i != 0:
next_page: Page = self.all_files[i - 1]
diff --git a/src/pyssg/page.py b/src/pyssg/page.py
index 26d2655..d39d8ef 100644
--- a/src/pyssg/page.py
+++ b/src/pyssg/page.py
@@ -7,37 +7,31 @@ log: Logger = getLogger(__name__)
class Page:
def __init__(self, name: str,
- ctime: float,
- mtime: float,
+ cts: float,
+ mts: float,
html: str,
toc: str,
toc_tokens: list[str],
meta: dict[str, Any],
- config: dict[str, Any],
- dir_config: dict[str, Any]) -> None:
- log.debug('initializing a page object with name "%s"', name)
+ config: dict[str, Any]) -> None:
# initial data
- self.name: str = name
- self.ctimestamp: float = ctime
- self.mtimestamp: float = mtime
+ self.name: str = name.replace(".md", ".html")
+ self.cts: float = cts
+ self.mts: float = mts
self.content: str = html
self.toc: str = toc
self.toc_tokens: list[str] = toc_tokens
self.meta: dict[str, Any] = meta
self.config: dict[str, Any] = config
- self.dir_config: dict[str, Any] = dir_config
# data from self.meta
self.title: str
self.author: list[str]
self.summary: str
self.lang: str
- self.cdatetime: datetime
- self.mdatetime: datetime | None = None
- self.tags: list[tuple[str, str]] = []
+ self.tags: tuple[str]
# constructed
- self.url: str
self.cdate_rss: str
self.cdate_sitemap: str
self.mdate_rss: str | None = None
@@ -52,7 +46,6 @@ class Page:
def __get_meta(self, var: str,
or_else: str | list[str] = ['']) -> str | list[str] | Any:
if var in self.meta:
- log.debug('getting metadata "%s"', var)
return self.meta[var]
else:
log.debug('getting metadata "%s" failed, using optional value "%s"',
@@ -61,7 +54,9 @@ class Page:
# these date/cdate/mdate might be a bit overcomplicated
- def __date(self, dt: datetime, format: str) -> str:
+ def date(self, ts: float, format: str) -> str:
+ dt: datetime = datetime.fromtimestamp(ts, tz=timezone.utc)
+
if format in self.config['fmt']:
return dt.strftime(self.config['fmt'][format])
else:
@@ -69,56 +64,20 @@ class Page:
'empty string', format)
return ''
- def cdate(self, format: str) -> str:
- return self.__date(self.cdatetime, format)
-
- def mdate(self, format: str) -> str:
- if self.mdatetime is None:
- log.warning('no mdatetime found, can\'t return a formatted string')
- return ''
- return self.__date(self.mdatetime, format)
-
- def from_timestamp(self, timestamp: float) -> datetime:
- return datetime.fromtimestamp(timestamp, tz=timezone.utc)
-
# parses meta from self.meta
def parse_metadata(self):
- log.debug('parsing metadata for file "%s"', self.name)
self.title = str(self.__get_meta('title')[0])
self.author = list(self.__get_meta('author'))
self.summary = str(self.__get_meta('summary')[0])
self.lang = str(self.__get_meta('lang', ['en'])[0])
- log.debug('parsing timestamp')
- self.cdatetime = self.from_timestamp(self.ctimestamp)
- self.cdate_rss = self.cdate('rss_date')
- self.cdate_sitemap = self.cdate('sitemap_date')
-
- if self.mtimestamp != 0.0:
- log.debug('parsing modified timestamp')
- self.mdatetime = self.from_timestamp(self.mtimestamp)
- self.mdate_rss = self.mdate('rss_date')
- self.mdate_sitemap = self.mdate('sitemap_date')
- else:
- log.debug('not parsing modified timestamp, hasn\'t been modified')
-
- if self.dir_config['tags']:
- log.debug('parsing tags')
- tags_only: list[str] = list(self.__get_meta('tags', []))
- if tags_only:
- tags_only.sort()
+ # probably add a way to sanitize tags
+ self.tags = tuple(set(sorted(self.__get_meta('tags', []))))
+ log.debug('parsed tags %s', self.tags)
- for t in tags_only:
- # need to specify dir_config['url'] as it is
- # a hardcoded tag url
- tag_url: str = f'{self.dir_config["url"]}/tag/@{t}.html'
- self.tags.append((t, tag_url))
- else:
- log.debug('no tags to parse')
+ self.cdate_rss = self.date(self.cts, 'rss_date')
+ self.cdate_sitemap = self.date(self.cts, 'sitemap_date')
+ if self.mts != 0.0:
+ self.mdate_rss = self.date(self.mts, 'rss_date')
+ self.mdate_sitemap = self.date(self.mts, 'sitemap_date')
- log.debug('parsing page url')
- # no need to specify dir_config['url'] as self.name already
- # contains the relative url
- name_html: str = self.name.replace(".md", ".html")
- self.url = f'{self.config["url"]["base"]}/{name_html}'
- log.debug('final url "%s"', self.url)
diff --git a/src/pyssg/plt/index.html b/src/pyssg/plt/index.html
index 7c034bb..23d890a 100644
--- a/src/pyssg/plt/index.html
+++ b/src/pyssg/plt/index.html
@@ -19,13 +19,13 @@
<ul>
{%for p in all_pages%}
{%if loop.previtem%}
- {%if loop.previtem.cdate('list_sep_date') != p.cdate('list_sep_date')%}
- <h3>{{p.cdate('list_sep_date')}}</h3>
+ {%if loop.previtem.date(loop.previtem.cts, 'list_sep_date') != p.date(p.cts, 'list_sep_date')%}
+ <h3>{{p.date(p.cts, 'list_sep_date')}}</h3>
{%endif%}
{%else%}
- <h3>{{p.cdate('list_sep_date')}}</h3>
+ <h3>{{p.date(p.cts, 'list_sep_date')}}</h3>
{%endif%}
- <li>{{p.cdate('list_date')}} - <a href="{{p.url}}">{{p.title}}</a></li>
+ <li>{{p.date(p.cts, 'list_date')}} - <a href="{{p.url}}">{{p.title}}</a></li>
{%endfor%}
</ul>
</body>
diff --git a/src/pyssg/plt/page.html b/src/pyssg/plt/page.html
index 93d4da9..b61ad03 100644
--- a/src/pyssg/plt/page.html
+++ b/src/pyssg/plt/page.html
@@ -8,9 +8,9 @@
<body>
<h1>{{page.title}}</h1>
<p>By {{page.author}}</p>
- <p>Created: {{page.cdate('date')}}</p>
- {%if page.mdatetime is not none%}
- <p>Modified: {{page.mdate('date')}}</p>
+ <p>Created: {{page.date(page.cts, 'date')}}</p>
+ {%if page.mtimestamp != 0.0%}
+ <p>Modified: {{page.date(page.mts, 'date')}}</p>
{%endif%}
{{page.content}}
diff --git a/src/pyssg/plt/tag.html b/src/pyssg/plt/tag.html
index aff7982..bf15c0d 100644
--- a/src/pyssg/plt/tag.html
+++ b/src/pyssg/plt/tag.html
@@ -13,13 +13,13 @@
<ul>
{%for p in tag_pages%}
{%if loop.previtem%}
- {%if loop.previtem.cdate('list_sep_date') != p.cdate('list_sep_date')%}
- <h3>{{p.cdate('list_sep_date')}}</h3>
+ {%if loop.previtem.date(loop.previtem.cts, 'list_sep_date') != p.date(p.cts, 'list_sep_date')%}
+ <h3>{{p.date(p.cts, 'list_sep_date')}}</h3>
{%endif%}
{%else%}
- <h3>{{p.cdate('list_sep_date')}}</h3>
+ <h3>{{p.date(p.cts, 'list_sep_date')}}</h3>
{%endif%}
- <li>{{p.cdate('list_date')}} - <a href="{{p.url}}">{{p.title}}</a></li>
+ <li>{{p.date(p.cts, 'list_date')}} - <a href="{{p.url}}">{{p.title}}</a></li>
{%endfor%}
</ul>
</body>
--
cgit v1.2.3-70-g09d2