This is an automated email from the ASF dual-hosted git repository. wave pushed a commit to branch main in repository https://gitbox.apache.org/repos/asf/bval-site.git
commit a85b13e9b1f89f940cc00f16da7f36ed97cf03e4 Author: Dave Fisher <[email protected]> AuthorDate: Tue Jun 1 11:41:13 2021 -0700 Fixes. Need asfgenid.py plugin for permalinks --- content/building.md | 14 +- content/downloads.md | 69 ++++----- content/samples.md | 2 +- pelicanconf.py | 24 +-- theme/plugins/README.md | 3 - theme/plugins/asfgenid.py | 384 ++++++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 438 insertions(+), 58 deletions(-) diff --git a/content/building.md b/content/building.md index 7cdcfe1..56450d5 100644 --- a/content/building.md +++ b/content/building.md @@ -48,15 +48,15 @@ command. You may also want to add a maven central mirror repository to your 1. Checkout the source as described above 1. Build the source using Maven as described above -```sh - mvn eclipse:eclipse -``` + ```sh + mvn eclipse:eclipse + ``` - If this is the first project in your workspace to use maven artifacts you need to create a classpath variable named M2_REPO which contains the full path to your local repository. The eclipse plugin can do this for you with the following command: + If this is the first project in your workspace to use maven artifacts you need to create a classpath variable named M2_REPO which contains the full path to your local repository. The eclipse plugin can do this for you with the following command: -```sh - mvn eclipse:configure-workspace -Declipse.workspace=$ {path_to_your_workspace} -``` + ```sh + mvn eclipse:configure-workspace -Declipse.workspace=$ {path_to_your_workspace} + ``` 1. Start Eclipse (3.4 or later suggested) and create a new workspace 1. Import the BVal project, by: diff --git a/content/downloads.md b/content/downloads.md index 6153634..25c649a 100644 --- a/content/downloads.md +++ b/content/downloads.md @@ -18,7 +18,7 @@ how to verify the integrity of downloaded files. #### Apache BVal 2.0.5 - Java 8 - Bean Validation v2.0 - Released October 26 2020 Module | Artifact | Signatures | Comments -- | - | - | - +--|--|--|-- Source Distribution | [bval-parent-2.0.5-source-release.zip][src202] | [asc][src-asc202] [sha512][src-sha512202] | - JSR380 Implementation | [bval-jsr-2.0.5.jar][jsr202] | [asc][jsr-asc202] [md5][jsr-md5202] [sha1][jsr-sha1202] | `javax.validation.spi.ValidationProvider` Implementation Bundle | [org.apache.bval.bundle-2.0.5.jar][bundle202] | [asc][bundle-asc202] [md5][bundle-md5202] [sha1][bundle-sha1202] | `javax.validation.spi.ValidationProvider` w/ OSGi metadata (includes `bval-jsr`) @@ -43,7 +43,7 @@ Extra Routines and Constraints | [bval-extras-2.0.5.jar][bvextras202] | [asc][bv #### Apache BVal 1.1.2 - Java 6 - Bean Validation v1.1 - Released Nov 3 2016 Module | Artifact | Signatures | Comments -- | - | - | - +--|--|--|-- Source Distribution | [bval-parent-1.1.2-source-release.zip][src112] | [asc][src-asc112] [md5][src-md5112] [sha1][src-sha1112] | - Core Framework | [bval-core-1.1.2.jar][core112] | [asc][core-asc112] [md5][core-md5112] [sha1][core-sha1112] | - JSR349 Implementation | [bval-jsr-1.1.2.jar][jsr112] | [asc][jsr-asc112] [md5][jsr-md5112] [sha1][jsr-sha1112] | `javax.validation.spi.ValidationProvider` (requires `bval-core`) @@ -86,7 +86,7 @@ Note: this release depends on geronimo-validation_1.1_spec API jar or any offici #### Apache BVal 0.5 - Java 5 - Bean Validation v1.0 - Released September 21, 2012 Module | Artifact | Signatures | Comments -- | - | - | - +--|--|--|-- Source Distribution | [bval-parent-0.5-source-release.zip][src] | [asc][src-asc] [md5][src-md5] [sha1][src-sha1] | - Core Framework | [bval-core-0.5.jar][core] | [asc][core-asc] [md5][core-md5] [sha1][core-sha1] | - JSR303 Implementation | [bval-jsr303-0.5.jar][jsr303] | [asc][jsr303-asc] [md5][jsr303-md5] [sha1][jsr303-sha1] | `javax.validation.spi.ValidationProvider` (requires `bval-core`) @@ -160,17 +160,16 @@ You'll need to add the following dependencies in your builds (and Maven will automatically include the additional transitive dependencies for you): ```html - - <dependency> - <groupId>org.apache.geronimo.specs</groupId> - <artifactId>geronimo-validation_1.0_spec</artifactId> - <version>1.1</version> - </dependency> - <dependency> - <groupId>org.apache.bval</groupId> - <artifactId>org.apache.bval.bundle</artifactId> - <version>0.5</version> - </dependency> +<dependency> + <groupId>org.apache.geronimo.specs</groupId> + <artifactId>geronimo-validation_1.0_spec</artifactId> + <version>1.1</version> +</dependency> +<dependency> + <groupId>org.apache.bval</groupId> + <artifactId>org.apache.bval.bundle</artifactId> + <version>0.5</version> +</dependency> ``` Maven will determine the transitive dependencies for the artifacts, but if @@ -178,21 +177,21 @@ you are not using Maven to build your project, then you will also need the following dependencies on the classpath: ```html - <dependency> - <groupId>org.apache.commons</groupId> - <artifactId>commons-lang3</artifactId> - <version>3.1</version> - </dependency> - <dependency> - <groupId>org.slf4j</groupId> - <artifactId>slf4j-simple</artifactId> - <version>1.6.1</version> - </dependency> - <dependency> - <groupId>commons-beanutils</groupId> - <artifactId>commons-beanutils</artifactId> - <version>1.8.3</version> - </dependency> +<dependency> + <groupId>org.apache.commons</groupId> + <artifactId>commons-lang3</artifactId> + <version>3.1</version> +</dependency> +<dependency> + <groupId>org.slf4j</groupId> + <artifactId>slf4j-simple</artifactId> + <version>1.6.1</version> +</dependency> +<dependency> + <groupId>commons-beanutils</groupId> + <artifactId>commons-beanutils</artifactId> + <version>1.8.3</version> +</dependency> ``` <a name="Downloads-VerifyingReleases"></a> @@ -212,22 +211,22 @@ rather than from a Then verify the signatures using: ```sh - $ pgpk -a KEYS - $ pgpv bval-parent-0.5-source-release.zip.asc +$ pgpk -a KEYS +$ pgpv bval-parent-0.5-source-release.zip.asc ``` or ```sh - $ pgp -ka KEYS - $ pgp bval-parent-0.5-source-release.zip.asc +$ pgp -ka KEYS +$ pgp bval-parent-0.5-source-release.zip.asc ``` or ```sh - $ gpg --import KEYS - $ gpg --verify bval-parent-0.5-source-release.zip.asc +$ gpg --import KEYS +$ gpg --verify bval-parent-0.5-source-release.zip.asc ``` Alternatively, you can verify the MD5 signature on the files. A Unix/Linux diff --git a/content/samples.md b/content/samples.md index 1a28c93..2d80181 100644 --- a/content/samples.md +++ b/content/samples.md @@ -1,6 +1,6 @@ Title: Samples -other projects at Apache, and other external projects that use a ASL 2.0 +Here we have collected some Bean Validation samples from our project, other projects at Apache, and other external projects that use a ASL 2.0 friendly license. Enjoy! <a name="Samples-bval-samples"></a> diff --git a/pelicanconf.py b/pelicanconf.py index 1754726..c5d8360 100644 --- a/pelicanconf.py +++ b/pelicanconf.py @@ -100,7 +100,7 @@ THEME = './theme/apache' PLUGIN_PATHS = ['./theme/plugins'] # PLUGINS = ['asfgenid', 'asfdata', 'pelican-gfm', 'asfreader'] # We are using the default plugin - 'pelican-gfm' which is installed by the build -PLUGINS = ['pelican-gfm'] +PLUGINS = ['asfgenid', 'pelican-gfm'] # Lifecycle and plugins: # (1) Initialization: @@ -124,17 +124,17 @@ PLUGINS = ['pelican-gfm'] # } # Configure the asfgenid plugin -# ASF_GENID = { -# 'metadata': True, -# 'elements': True, -# 'headings': True, -# 'headings_re': r'^h[1-4]', -# 'permalinks': True, -# 'toc': True, -# 'toc_headers': r"h[1-4]", -# 'tables': True, -# 'debug': False -# } +ASF_GENID = { + 'metadata': False, + 'elements': False, + 'headings': True, + 'headings_re': r'^h[1-4]', + 'permalinks': True, + 'toc': False, + 'toc_headers': r"h[1-4]", + 'tables': True, + 'debug': False +} # Sitemap Generator # SITEMAP = { diff --git a/theme/plugins/README.md b/theme/plugins/README.md deleted file mode 100644 index cf8c404..0000000 --- a/theme/plugins/README.md +++ /dev/null @@ -1,3 +0,0 @@ -# Placeholder - -Need to have this directory to receive the standard plugins diff --git a/theme/plugins/asfgenid.py b/theme/plugins/asfgenid.py new file mode 100644 index 0000000..f0ff875 --- /dev/null +++ b/theme/plugins/asfgenid.py @@ -0,0 +1,384 @@ +''' +asfgenid +=================================== +Generates HeadingIDs, ElementID, and PermaLinks +First find all specified IDs and classes. Assure unique ID and permalink +Next find all headings missing IDs. Assure unique ID and permalink +Generates a Table of Content +''' + +# from __future__ import unicode_literals + +import sys +import traceback +import re +import unicodedata + +from bs4 import BeautifulSoup, Comment + +import pelican.contents +import pelican.plugins.signals + +''' +Based on +https://github.com/waylan/Python-Markdown/blob/master/markdown/extensions/headerid.py +Which is BSD licensed, but is very much rewritten. +''' + +ASF_GENID = { + 'metadata': True, # {{ metadata }} inclusion of data in the html. + 'elements': True, # {#id} and {.class} annotations. + 'headings': True, # add slugified id to headings missing id. Can be overridden by page metadata. + 'headings_re': r'^h[1-6]', # regex for which headings to check. + 'permalinks': True, # add permalinks to elements and headings when id is added. + 'toc': True, # check for [TOC] and add Table of Content if present. + 'toc_headers': r'h[1-6]', # regex for which headings to include in the [TOC] + 'tables': True, # add class="table" for tables missing class. + 'debug': False +} + +# Fixup tuples for HTML that GFM makes into text. +FIXUP_UNSAFE = [ + (re.compile(r'<script'),'<script'), + (re.compile(r'</script'),'</script'), + (re.compile(r'<style'),'<style'), + (re.compile(r'</style'),'</style'), + (re.compile(r'<iframe'),'<iframe'), + (re.compile(r'</iframe'),'</iframe') +] + +# Find {{ metadata }} inclusions +METADATA_RE = re.compile(r'{{\s*(?P<meta>[-_:a-zA-Z0-9]+)\s*}}') + +# Find {#id} or {.class} elementid annotations +ELEMENTID_RE = re.compile(r'(?:[ \t]*[{\[][ \t]*(?P<type>[#.])(?P<id>[-._:a-zA-Z0-9 ]+)[}\]])(\n|$)') + +# ID duplicates match +IDCOUNT_RE = re.compile(r'^(.*)_([0-9]+)$') + +# For permalinks +LINK_CHAR = 'ΒΆ' + +# strip permalink chars from headings for ToC +PARA_MAP = { + ord(LINK_CHAR): None +} + +# Find table tags - to check for ones without class attribute. +TABLE_RE = re.compile(r'^table') + +# An item in a Table of Contents - from toc.py +class HtmlTreeNode(object): + def __init__(self, parent, header, level, id): + self.children = [] + self.parent = parent + self.header = header + self.level = level + self.id = id + + def add(self, new_header): + new_level = new_header.name + new_string = new_header.string + new_id = new_header.attrs.get('id') + + if not new_string: + new_string = new_header.find_all( + text=lambda t: not isinstance(t, Comment), + recursive=True) + new_string = ''.join(new_string) + new_string = new_string.translate(PARA_MAP) + + if self.level < new_level: + new_node = HtmlTreeNode(self, new_string, new_level, new_id) + self.children += [new_node] + return new_node, new_header + elif self.level == new_level: + new_node = HtmlTreeNode(self.parent, new_string, new_level, new_id) + self.parent.children += [new_node] + return new_node, new_header + elif self.level > new_level: + return self.parent.add(new_header) + + def __str__(self): + ret = '' + if self.parent: + ret = "<a class='toc-href' href='#{0}' title='{1}'>{1}</a>".format( + self.id, self.header) + + if self.children: + ret += "<ul>{}</ul>".format('{}' * len(self.children)).format( + *self.children) + + if self.parent: + ret = "<li>{}</li>".format(ret) + + if not self.parent: + ret = "<div id='toc'>{}</div>".format(ret) + + return ret + + +# assure configuration +def init_default_config(pelican): + from pelican.settings import DEFAULT_CONFIG + + DEFAULT_CONFIG.setdefault('ASF_GENID', ASF_GENID) + if(pelican): + pelican.settings.setdefault('ASF_GENID', ASF_GENID) + + +# from Apache CMS markdown/extensions/headerid.py - slugify in the same way as the Apache CMS +def slugify(value, separator): + """ Slugify a string, to make it URL friendly. """ + value = unicodedata.normalize('NFKD', value).encode('ascii', 'ignore') + value = re.sub('[^\\w\\s-]', '', value.decode('ascii')).strip().lower() + return re.sub('[%s\\s]+' % separator, separator, value) + + +# Ensure an id is unique in a set of ids. Append '_1', '_2'... if not +def unique(id, ids): + while id in ids or not id: + m = IDCOUNT_RE.match(id) + print(f'id="{id}" is a duplicate') + if m: + id = '%s_%d' % (m.group(1), int(m.group(2)) + 1) + else: + id = '%s_%d' % (id, 1) + ids.add(id) + return id + + +# append a permalink +def permalink(soup, mod_element): + new_tag = soup.new_tag('a', href='#' + mod_element['id']) + new_tag['class'] = 'headerlink' + new_tag['title'] = 'Permalink' + new_tag.string = LINK_CHAR + mod_element.append(new_tag) + + +# fixup cmark content - note that this may be too hungry. It may need to occur later and skipped in codeblock and pre tags. +def fixup_content(content): + text = content._content + modified = False + # Find messed up html + for regex, replace in FIXUP_UNSAFE: + m = regex.search(text) + if m: + modified = True + text = re.sub(regex, replace, text) + if modified: + content._content = text + + +# expand metadata found in {{ key }} +def expand_metadata(tag, metadata): + this_string = str(tag.string) + m = 1 + modified = False + while m: + m = METADATA_RE.search(this_string) + if m: + this_data = m.group(1).strip() + format_string = '{{{0}}}'.format(this_data) + try: + new_string = format_string.format(**metadata) + print(f'{{{{{m.group(1)}}}}} -> {new_string}') + except Exception: + # the data expression was not found + print(f'{{{{{m.group(1)}}}}} is not found') + new_string = format_string + # replace the first pattern with the new_string + this_string = re.sub(METADATA_RE, new_string, this_string, count=1) + modified = True + if modified: + tag.string.replace_with(this_string) + + +# do elementid transformation for {#id} and {.class} attribute annotations. +def elementid_transform(ids, soup, tag, permalinks, perma_set, debug): + tagnav = tag.parent + this_string = str(tag.string) + if debug: + print(f'name = {tagnav.name}, string = {this_string}') + if tagnav.name not in ['[document]', 'code', 'pre']: + m = ELEMENTID_RE.search(tag.string) + if m: + # this replacement could be better it truncates and likely drops additional annotations + tag.string.replace_with(this_string[:m.start()]) + if m.group('type') == '#': + # id attribute annotation + tagnav['id'] = unique(m.group('id'), ids) + if permalinks: + permalink(soup, tagnav) + unique(tagnav['id'], perma_set) + if debug: + print(f'# insertion {tagnav}') + else: + # class attribute annotation (regex only recognizes the two types) + tagnav['class'] = m.group('id') + if debug: + print(f'Class {tag.name} : {tagnav["class"]}') + + +# generate id for a heading +def headingid_transform(ids, soup, tag, permalinks, perma_set): + new_string = tag.string + if not new_string: + # roll up strings if no immediate string + new_string = tag.find_all( + text=lambda t: not isinstance(t, Comment), + recursive=True) + new_string = ''.join(new_string) + + # don't have an id create it from text + new_id = slugify(new_string, '-') + tag['id'] = unique(new_id, ids) + if permalinks: + permalink(soup, tag) + # inform if there is a duplicate permalink + unique(tag['id'], perma_set) + + +# generate table of contents from headings after [TOC] content +def generate_toc(content, tags, title, toc_headers): + settoc = False + tree = node = HtmlTreeNode(None, title, 'h0', '') + # find the last [TOC] + taglast = tags[0] + for tag in tags: + taglast = tag + # find all headings after the final [TOC] + heading_re = re.compile(toc_headers) + for header in taglast.findAllNext(heading_re): + # we have heading content for the ToC + settoc = True + # add the heading. + node, _new_header = node.add(header) + # convert the ToC to Beautiful Soup + tree_soup = '' + if settoc: + print(' ToC') + # convert the HtmlTreeNode into Beautiful Soup + tree_string = '{}'.format(tree) + tree_soup = BeautifulSoup(tree_string, 'html.parser') + # Make the ToC availble to the theme's template + content.toc = tree_soup.decode(formatter='html') + # replace the first [TOC] with the generated table of contents + for tag in tags: + tag.replaceWith(tree_soup) + # replace additional [TOC] with nothing + tree_soup = '' + + +# add the asfdata metadata into GFM content. +def add_data(content): + """ Mix in ASF data as metadata """ + + # if the reader is 'asf' then the asf metadata is already in place during asfreader plugin. + if content.metadata.get('reader') != 'asf': + asf_metadata = content.settings.get('ASF_DATA', { }).get('metadata') + if asf_metadata: + content.metadata.update(asf_metadata) + + +# main worker transforming the html +def generate_id(content): + if isinstance(content, pelican.contents.Static): + return + + # track the id tags + ids = set() + # track permalinks + permalinks = set() + + # step 1 - fixup html that cmark marks unsafe - move to later? + fixup_content(content) + + # step 2 - prepare for genid processes + # parse html content into BeautifulSoup4 + soup = BeautifulSoup(content._content, 'html.parser') + # page title + title = content.metadata.get('title', 'Title') + # assure relative source path is in the metadata + content.metadata['relative_source_path'] = content.relative_source_path + # display output path and title + print(f'{content.relative_source_path} - {title}') + # enhance metadata if done by asfreader + add_data(content) + # get plugin settings + asf_genid = content.settings['ASF_GENID'] + # asf_headings setting may be overridden + asf_headings = content.metadata.get('asf_headings', str(asf_genid['headings'])) + # show active plugins + if asf_genid['debug']: + print('asfgenid:\nshow plugins in case one is processing before this one') + for name in content.settings['PLUGINS']: + print(f'plugin: {name}') + + # step 3 - metadata expansion + if asf_genid['metadata']: + if asf_genid['debug']: + print(f'metadata expansion: {content.relative_source_path}') + for tag in soup.findAll(string=METADATA_RE): + expand_metadata(tag, content.metadata) + + # step 4 - find all id attributes already present + for tag in soup.findAll(id=True): + unique(tag['id'], ids) + # don't change existing ids + + # step 5 - find all {#id} and {.class} text and assign attributes + if asf_genid['elements']: + if asf_genid['debug']: + print(f'elementid: {content.relative_source_path}') + for tag in soup.findAll(string=ELEMENTID_RE): + elementid_transform(ids, soup, tag, asf_genid['permalinks'], permalinks, asf_genid['debug']) + + # step 6 - find all headings w/o ids already present or assigned with {#id} text + if asf_headings == 'True': + if asf_genid['debug']: + print(f'headings: {content.relative_source_path}') + # Find heading tags + HEADING_RE = re.compile(asf_genid['headings_re']) + for tag in soup.findAll(HEADING_RE, id=False): + headingid_transform(ids, soup, tag, asf_genid['permalinks'], permalinks) + + # step 7 - find all tables without class + if asf_genid['tables']: + if asf_genid['debug']: + print(f'tables: {content.relative_source_path}') + for tag in soup.findAll(TABLE_RE, _class=False): + tag['class'] = 'table' + + # step 8 - find TOC tag and generate Table of Contents + if asf_genid['toc']: + tags = soup('p', text='[TOC]') + if tags: + generate_toc(content, tags, title, asf_genid['toc_headers']) + + # step 9 - reset the html content + content._content = soup.decode(formatter='html') + + # step 10 - output all of the permalinks created + for tag in permalinks: + print(f' #{tag}') + + +def tb_connect(pel_ob): + """Print any exception, before Pelican chews it into nothingness.""" + try: + generate_id(pel_ob) + except: + print('-----', file=sys.stderr) + print('FATAL: %s' % (pel_ob.relative_source_path), file=sys.stderr) + traceback.print_exc() + # if we have errors in this module then we want to quit to avoid erasing the site + sys.exit(4) + + +def register(): + pelican.plugins.signals.initialized.connect(init_default_config) + + +pelican.plugins.signals.content_object_init.connect(tb_connect)
