discourse/lib/cooked_post_processor.rb

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

456 lines
14 KiB
Ruby
Raw Normal View History

# frozen_string_literal: true
# Post processing that we can do after a post has already been cooked.
2013-07-07 19:39:08 -04:00
# For example, inserting the onebox content, or image sizes/thumbnails.
2013-02-05 14:16:51 -05:00
class CookedPostProcessor
include CookedProcessorMixin
PERF: Improve quality of `PostSearchData#raw_data`. (#7275) This commit fixes the follow quality issue with `PostSearchData#raw_data`: 1. URLs are being tokenized and links with similar href and characters are being duplicated in the raw data. `Post#cooked`: ``` <p><a href=\"https://meta.discourse.org/some.png\" class=\"onebox\" target=\"_blank\" rel=\"nofollow noopener\">https://meta.discourse.org/some.png</a></p> ``` `PostSearchData#raw_data` Before: ``` This is a test topic 0 Uncategorized https://meta.discourse.org/some.png discourse org/some png https://meta.discourse.org/some.png discourse org/some png ``` `PostSearchData#raw_data` After: ``` This is a test topic 0 Uncategorized https://meta.discourse.org/some.png meta discourse org ``` 2. Ligthbox being included in search pollutes the `PostSearchData#raw_data` unncessarily. From 28 March 2018 to 28 March 2019, searches for the term `image` on `meta.discourse.org` had a click through rate of 2.1%. Non-lightboxed images are not included in indexing for search yet we were indexing content within a lightbox. Also, search for terms like `image` was affected we were using `Pasted image` as the filename for uploads that were pasted. `Post#cooked` ``` <p>Let me see how I can fix this image<br>\n<div class=\"lightbox-wrapper\"><a class=\"lightbox\" href=\"https://meta.discourse.org/some.png\" title=\"some.png\" rel=\"nofollow noopener\"><img src=\"https://meta.discourse.org/some.png\" width=\"275\" height=\"299\"><div class=\"meta\">\n<svg class=\"fa d-icon d-icon-far-image svg-icon\" aria-hidden=\"true\"><use xlink:href=\"#far-image\"></use></svg><span class=\"filename\">some.png</span><span class=\"informations\">1750×2000</span><svg class=\"fa d-icon d-icon-discourse-expand svg-icon\" aria-hidden=\"true\"><use xlink:href=\"#discourse-expand\"></use></svg>\n</div></a></div></p> ``` `PostSearchData#raw_data` Before: ``` This is a test topic 0 Uncategorized Let me see how I can fix this image some.png png https://meta.discourse.org/some.png discourse org/some png some.png png 1750×2000 ``` `PostSearchData#raw_data` After: ``` This is a test topic 0 Uncategorized Let me see how I can fix this image ``` In terms of indexing performance, we now have to parse the given HTML through nokogiri twice. However performance is not a huge worry here since a string length of 194170 takes only 30ms to scrub plus the indexing takes place in a background job.
2019-03-31 22:14:29 -04:00
LIGHTBOX_WRAPPER_CSS_CLASS = "lightbox-wrapper"
GIF_SOURCES_REGEXP = %r{(giphy|tenor)\.com/}
attr_reader :cooking_options, :doc
2013-02-05 14:16:51 -05:00
def initialize(post, opts = {})
@dirty = false
@opts = opts
@post = post
@model = post
@previous_cooked = (@post.cooked || "").dup
# NOTE: we re-cook the post here in order to prevent timing issues with edits
# cf. https://meta.discourse.org/t/edit-of-rebaked-post-doesnt-show-in-html-only-in-raw/33815/6
@cooking_options = post.cooking_options || opts[:cooking_options] || {}
@cooking_options[:topic_id] = post.topic_id
@cooking_options = @cooking_options.symbolize_keys
@with_secure_uploads = @post.with_secure_uploads?
@category_id = @post&.topic&.category_id
2016-04-12 14:09:59 -04:00
cooked = post.cook(post.raw, @cooking_options)
@doc = Loofah.fragment(cooked)
@has_oneboxes = post.post_analyzer.found_oneboxes?
2013-02-19 01:57:14 -05:00
@size_cache = {}
@disable_dominant_color = !!opts[:disable_dominant_color]
@omit_nofollow = post.omit_nofollow?
2013-02-05 14:16:51 -05:00
end
def post_process(new_post: false)
DistributedMutex.synchronize("post_process_#{@post.id}", validity: 10.minutes) do
DiscourseEvent.trigger(:before_post_process_cooked, @doc, @post)
remove_full_quote_on_direct_reply if new_post
post_process_oneboxes
post_process_images
add_blocked_hotlinked_media_placeholders
post_process_quotes
optimize_urls
remove_user_ids
update_post_image
2017-10-23 13:09:38 -04:00
enforce_nofollow
grant_badges
@post.link_post_uploads(fragments: @doc)
2017-06-23 14:35:10 -04:00
DiscourseEvent.trigger(:post_process_cooked, @doc, @post)
nil
end
end
2016-04-06 12:02:18 -04:00
def has_emoji?
(@doc.css("img.emoji") - @doc.css(".quote img")).size > 0
end
def grant_badges
return if @post.user.blank? || !Guardian.new.can_see?(@post)
2016-04-13 16:38:24 -04:00
BadgeGranter.grant(Badge.find(Badge::FirstEmoji), @post.user, post_id: @post.id) if has_emoji?
if @has_oneboxes
BadgeGranter.grant(Badge.find(Badge::FirstOnebox), @post.user, post_id: @post.id)
end
if @post.is_reply_by_email?
BadgeGranter.grant(Badge.find(Badge::FirstReplyByEmail), @post.user, post_id: @post.id)
end
2013-02-05 14:16:51 -05:00
end
def post_process_quotes
@doc
.css("aside.quote")
.each do |q|
post_number = q["data-post"]
topic_id = q["data-topic"]
if topic_id && post_number
comparer = QuoteComparer.new(topic_id.to_i, post_number.to_i, q.css("blockquote").text)
q["class"] = ((q["class"] || "") + " quote-post-not-found").strip if comparer.missing?
q["class"] = ((q["class"] || "") + " quote-modified").strip if comparer.modified?
end
end
end
def remove_full_quote_on_direct_reply
return if !SiteSetting.remove_full_quote
return if @post.post_number == 1
return if @doc.xpath("aside[contains(@class, 'quote')]").size != 1
previous =
Post
.where(
"post_number < ? AND topic_id = ? AND post_type = ? AND NOT hidden",
@post.post_number,
@post.topic_id,
Post.types[:regular],
)
.order("post_number DESC")
.limit(1)
.pluck(:cooked)
.first
return if previous.blank?
previous_text = Nokogiri::HTML5.fragment(previous).text.strip
quoted_text = @doc.css("aside.quote:first-child blockquote").first&.text&.strip || ""
return if previous_text.gsub(/(\s){2,}/, '\1') != quoted_text.gsub(/(\s){2,}/, '\1')
quote_regexp = %r{\A\s*\[quote.+\[/quote\]}im
quoteless_raw = @post.raw.sub(quote_regexp, "").strip
return if @post.raw.strip == quoteless_raw
PostRevisor.new(@post).revise!(
Discourse.system_user,
{ raw: quoteless_raw, edit_reason: I18n.t(:removed_direct_reply_full_quotes) },
skip_validations: true,
bypass_bump: true,
)
end
2013-07-07 19:39:08 -04:00
def extract_images
# all images with a src attribute
@doc.css("img[src], img[#{PrettyText::BLOCKED_HOTLINKED_SRC_ATTR}]") -
# minus data images
@doc.css("img[src^='data']") -
# minus emojis
@doc.css("img.emoji")
2013-07-07 19:39:08 -04:00
end
def extract_images_for_post
# all images with a src attribute
@doc.css("img[src]") -
# minus emojis
@doc.css("img.emoji") -
# minus images inside quotes
@doc.css(".quote img") -
# minus onebox site icons
@doc.css("img.site-icon") -
# minus onebox avatars
@doc.css("img.onebox-avatar") - @doc.css("img.onebox-avatar-inline") -
# minus github onebox profile images
@doc.css(".onebox.githubfolder img")
end
2013-11-05 13:04:47 -05:00
def convert_to_link!(img)
w, h = img["width"].to_i, img["height"].to_i
user_width, user_height =
(w > 0 && h > 0 && [w, h]) || get_size_from_attributes(img) ||
get_size_from_image_sizes(img["src"], @opts[:image_sizes])
limit_size!(img)
2013-02-19 01:57:14 -05:00
src = img["src"]
return if src.blank? || is_a_hyperlink?(img) || is_svg?(img)
2013-02-19 01:57:14 -05:00
upload = Upload.get_from_url(src)
original_width, original_height = nil
if (upload.present?)
original_width = upload.width || 0
original_height = upload.height || 0
else
original_width, original_height = (get_size(src) || [0, 0]).map(&:to_i)
if original_width == 0 || original_height == 0
Rails.logger.info "Can't reach '#{src}' to get its dimension."
return
end
end
if (upload.present? && upload.animated?) || src.match?(GIF_SOURCES_REGEXP)
img.add_class("animated")
end
if original_width <= SiteSetting.max_image_width &&
original_height <= SiteSetting.max_image_height
return
end
2013-07-07 19:39:08 -04:00
user_width, user_height = [original_width, original_height] if user_width.to_i <= 0 &&
user_height.to_i <= 0
width, height = user_width, user_height
crop =
SiteSetting.min_ratio_to_crop > 0 && width.to_f / height.to_f < SiteSetting.min_ratio_to_crop
if crop
width, height = ImageSizer.crop(width, height)
img["width"], img["height"] = width, height
else
width, height = ImageSizer.resize(width, height)
end
if upload.present?
upload.create_thumbnail!(width, height, crop: crop)
each_responsive_ratio do |ratio|
resized_w = (width * ratio).to_i
resized_h = (height * ratio).to_i
if upload.width && resized_w <= upload.width
upload.create_thumbnail!(resized_w, resized_h, crop: crop)
end
end
return if upload.animated?
if img.ancestors(".onebox, .onebox-body, .quote").blank? && !img.classes.include?("onebox")
add_lightbox!(img, original_width, original_height, upload, cropped: crop)
end
optimize_image!(img, upload, cropped: crop)
end
2013-07-07 19:39:08 -04:00
end
def each_responsive_ratio
SiteSetting
.responsive_post_image_sizes
.split("|")
.map(&:to_f)
.sort
.each { |r| yield r if r > 1 }
end
def optimize_image!(img, upload, cropped: false)
w, h = img["width"].to_i, img["height"].to_i
# note: optimize_urls cooks the src further after this
thumbnail = upload.thumbnail(w, h)
if thumbnail && thumbnail.filesize.to_i < upload.filesize
img["src"] = thumbnail.url
srcset = +""
each_responsive_ratio do |ratio|
resized_w = (w * ratio).to_i
resized_h = (h * ratio).to_i
if !cropped && upload.width && resized_w > upload.width
cooked_url = UrlHelper.cook_url(upload.url, secure: @post.with_secure_uploads?)
srcset << ", #{cooked_url} #{ratio.to_s.sub(/\.0$/, "")}x"
elsif t = upload.thumbnail(resized_w, resized_h)
cooked_url = UrlHelper.cook_url(t.url, secure: @post.with_secure_uploads?)
srcset << ", #{cooked_url} #{ratio.to_s.sub(/\.0$/, "")}x"
end
img[
"srcset"
] = "#{UrlHelper.cook_url(img["src"], secure: @post.with_secure_uploads?)}#{srcset}" if srcset.present?
end
else
img["src"] = upload.url
end
if !@disable_dominant_color &&
(color = upload.dominant_color(calculate_if_missing: true).presence)
img["data-dominant-color"] = color
end
end
def add_lightbox!(img, original_width, original_height, upload, cropped: false)
2013-06-25 20:44:20 -04:00
# first, create a div to hold our lightbox
PERF: Improve quality of `PostSearchData#raw_data`. (#7275) This commit fixes the follow quality issue with `PostSearchData#raw_data`: 1. URLs are being tokenized and links with similar href and characters are being duplicated in the raw data. `Post#cooked`: ``` <p><a href=\"https://meta.discourse.org/some.png\" class=\"onebox\" target=\"_blank\" rel=\"nofollow noopener\">https://meta.discourse.org/some.png</a></p> ``` `PostSearchData#raw_data` Before: ``` This is a test topic 0 Uncategorized https://meta.discourse.org/some.png discourse org/some png https://meta.discourse.org/some.png discourse org/some png ``` `PostSearchData#raw_data` After: ``` This is a test topic 0 Uncategorized https://meta.discourse.org/some.png meta discourse org ``` 2. Ligthbox being included in search pollutes the `PostSearchData#raw_data` unncessarily. From 28 March 2018 to 28 March 2019, searches for the term `image` on `meta.discourse.org` had a click through rate of 2.1%. Non-lightboxed images are not included in indexing for search yet we were indexing content within a lightbox. Also, search for terms like `image` was affected we were using `Pasted image` as the filename for uploads that were pasted. `Post#cooked` ``` <p>Let me see how I can fix this image<br>\n<div class=\"lightbox-wrapper\"><a class=\"lightbox\" href=\"https://meta.discourse.org/some.png\" title=\"some.png\" rel=\"nofollow noopener\"><img src=\"https://meta.discourse.org/some.png\" width=\"275\" height=\"299\"><div class=\"meta\">\n<svg class=\"fa d-icon d-icon-far-image svg-icon\" aria-hidden=\"true\"><use xlink:href=\"#far-image\"></use></svg><span class=\"filename\">some.png</span><span class=\"informations\">1750×2000</span><svg class=\"fa d-icon d-icon-discourse-expand svg-icon\" aria-hidden=\"true\"><use xlink:href=\"#discourse-expand\"></use></svg>\n</div></a></div></p> ``` `PostSearchData#raw_data` Before: ``` This is a test topic 0 Uncategorized Let me see how I can fix this image some.png png https://meta.discourse.org/some.png discourse org/some png some.png png 1750×2000 ``` `PostSearchData#raw_data` After: ``` This is a test topic 0 Uncategorized Let me see how I can fix this image ``` In terms of indexing performance, we now have to parse the given HTML through nokogiri twice. However performance is not a huge worry here since a string length of 194170 takes only 30ms to scrub plus the indexing takes place in a background job.
2019-03-31 22:14:29 -04:00
lightbox = create_node("div", LIGHTBOX_WRAPPER_CSS_CLASS)
2013-07-07 19:39:08 -04:00
img.add_next_sibling(lightbox)
lightbox.add_child(img)
2013-06-25 20:44:20 -04:00
# then, the link to our larger image
src = UrlHelper.cook_url(img["src"], secure: @post.with_secure_uploads?)
a = create_link_node("lightbox", src)
2013-02-19 01:57:14 -05:00
img.add_next_sibling(a)
a["data-download-href"] = Discourse.store.download_url(upload) if upload
2013-02-19 01:57:14 -05:00
a.add_child(img)
2013-07-07 19:39:08 -04:00
2013-06-25 20:44:20 -04:00
# then, some overlay informations
meta = create_node("div", "meta")
2013-07-07 19:39:08 -04:00
img.add_next_sibling(meta)
2013-06-21 12:29:40 -04:00
2013-11-05 13:04:47 -05:00
filename = get_filename(upload, img["src"])
informations = +"#{original_width}×#{original_height}"
informations << " #{upload.human_filesize}" if upload
2013-06-21 12:29:40 -04:00
a["title"] = CGI.escapeHTML(img["title"] || img["alt"] || filename)
2013-11-29 14:03:39 -05:00
meta.add_child create_icon_node("far-image")
2016-08-10 23:27:12 -04:00
meta.add_child create_span_node("filename", a["title"])
2013-06-25 20:44:20 -04:00
meta.add_child create_span_node("informations", informations)
meta.add_child create_icon_node("discourse-expand")
2013-06-21 12:29:40 -04:00
end
2013-02-19 01:57:14 -05:00
def get_filename(upload, src)
return File.basename(src) unless upload
return upload.original_filename unless upload.original_filename =~ /^blob(\.png)?$/i
I18n.t("upload.pasted_image_filename")
end
def update_post_image
FEATURE: Include optimized thumbnails for topics (#9215) This introduces new APIs for obtaining optimized thumbnails for topics. There are a few building blocks required for this: - Introduces new `image_upload_id` columns on the `posts` and `topics` table. This replaces the old `image_url` column, which means that thumbnails are now restricted to uploads. Hotlinked thumbnails are no longer possible. In normal use (with pull_hotlinked_images enabled), this has no noticeable impact - A migration attempts to match existing urls to upload records. If a match cannot be found then the posts will be queued for rebake - Optimized thumbnails are generated during post_process_cooked. If thumbnails are missing when serializing a topic list, then a sidekiq job is queued - Topic lists and topics now include a `thumbnails` key, which includes all the available images: ``` "thumbnails": [ { "max_width": null, "max_height": null, "url": "//example.com/original-image.png", "width": 1380, "height": 1840 }, { "max_width": 1024, "max_height": 1024, "url": "//example.com/optimized-image.png", "width": 768, "height": 1024 } ] ``` - Themes can request additional thumbnail sizes by using a modifier in their `about.json` file: ``` "modifiers": { "topic_thumbnail_sizes": [ [200, 200], [800, 800] ], ... ``` Remember that these are generated asynchronously, so your theme should include logic to fallback to other available thumbnails if your requested size has not yet been generated - Two new raw plugin outlets are introduced, to improve the customisability of the topic list. `topic-list-before-columns` and `topic-list-before-link`
2020-05-05 04:07:50 -04:00
upload = nil
images = extract_images_for_post
FEATURE: Include optimized thumbnails for topics (#9215) This introduces new APIs for obtaining optimized thumbnails for topics. There are a few building blocks required for this: - Introduces new `image_upload_id` columns on the `posts` and `topics` table. This replaces the old `image_url` column, which means that thumbnails are now restricted to uploads. Hotlinked thumbnails are no longer possible. In normal use (with pull_hotlinked_images enabled), this has no noticeable impact - A migration attempts to match existing urls to upload records. If a match cannot be found then the posts will be queued for rebake - Optimized thumbnails are generated during post_process_cooked. If thumbnails are missing when serializing a topic list, then a sidekiq job is queued - Topic lists and topics now include a `thumbnails` key, which includes all the available images: ``` "thumbnails": [ { "max_width": null, "max_height": null, "url": "//example.com/original-image.png", "width": 1380, "height": 1840 }, { "max_width": 1024, "max_height": 1024, "url": "//example.com/optimized-image.png", "width": 768, "height": 1024 } ] ``` - Themes can request additional thumbnail sizes by using a modifier in their `about.json` file: ``` "modifiers": { "topic_thumbnail_sizes": [ [200, 200], [800, 800] ], ... ``` Remember that these are generated asynchronously, so your theme should include logic to fallback to other available thumbnails if your requested size has not yet been generated - Two new raw plugin outlets are introduced, to improve the customisability of the topic list. `topic-list-before-columns` and `topic-list-before-link`
2020-05-05 04:07:50 -04:00
@post.each_upload_url(fragments: images.css("[data-thumbnail]")) do |src, path, sha1|
FEATURE: Include optimized thumbnails for topics (#9215) This introduces new APIs for obtaining optimized thumbnails for topics. There are a few building blocks required for this: - Introduces new `image_upload_id` columns on the `posts` and `topics` table. This replaces the old `image_url` column, which means that thumbnails are now restricted to uploads. Hotlinked thumbnails are no longer possible. In normal use (with pull_hotlinked_images enabled), this has no noticeable impact - A migration attempts to match existing urls to upload records. If a match cannot be found then the posts will be queued for rebake - Optimized thumbnails are generated during post_process_cooked. If thumbnails are missing when serializing a topic list, then a sidekiq job is queued - Topic lists and topics now include a `thumbnails` key, which includes all the available images: ``` "thumbnails": [ { "max_width": null, "max_height": null, "url": "//example.com/original-image.png", "width": 1380, "height": 1840 }, { "max_width": 1024, "max_height": 1024, "url": "//example.com/optimized-image.png", "width": 768, "height": 1024 } ] ``` - Themes can request additional thumbnail sizes by using a modifier in their `about.json` file: ``` "modifiers": { "topic_thumbnail_sizes": [ [200, 200], [800, 800] ], ... ``` Remember that these are generated asynchronously, so your theme should include logic to fallback to other available thumbnails if your requested size has not yet been generated - Two new raw plugin outlets are introduced, to improve the customisability of the topic list. `topic-list-before-columns` and `topic-list-before-link`
2020-05-05 04:07:50 -04:00
upload = Upload.find_by(sha1: sha1)
break if upload
end
if upload.nil? # No specified thumbnail. Use any image:
@post.each_upload_url(fragments: images.css(":not([data-thumbnail])")) do |src, path, sha1|
upload = Upload.find_by(sha1: sha1)
break if upload
end
end
FEATURE: Include optimized thumbnails for topics (#9215) This introduces new APIs for obtaining optimized thumbnails for topics. There are a few building blocks required for this: - Introduces new `image_upload_id` columns on the `posts` and `topics` table. This replaces the old `image_url` column, which means that thumbnails are now restricted to uploads. Hotlinked thumbnails are no longer possible. In normal use (with pull_hotlinked_images enabled), this has no noticeable impact - A migration attempts to match existing urls to upload records. If a match cannot be found then the posts will be queued for rebake - Optimized thumbnails are generated during post_process_cooked. If thumbnails are missing when serializing a topic list, then a sidekiq job is queued - Topic lists and topics now include a `thumbnails` key, which includes all the available images: ``` "thumbnails": [ { "max_width": null, "max_height": null, "url": "//example.com/original-image.png", "width": 1380, "height": 1840 }, { "max_width": 1024, "max_height": 1024, "url": "//example.com/optimized-image.png", "width": 768, "height": 1024 } ] ``` - Themes can request additional thumbnail sizes by using a modifier in their `about.json` file: ``` "modifiers": { "topic_thumbnail_sizes": [ [200, 200], [800, 800] ], ... ``` Remember that these are generated asynchronously, so your theme should include logic to fallback to other available thumbnails if your requested size has not yet been generated - Two new raw plugin outlets are introduced, to improve the customisability of the topic list. `topic-list-before-columns` and `topic-list-before-link`
2020-05-05 04:07:50 -04:00
if upload.present?
@post.update_column(:image_upload_id, upload.id) # post
if @post.is_first_post? # topic
@post.topic.update_column(:image_upload_id, upload.id)
extra_sizes =
ThemeModifierHelper.new(theme_ids: Theme.user_selectable.pluck(:id)).topic_thumbnail_sizes
@post.topic.generate_thumbnails!(extra_sizes: extra_sizes)
end
else
@post.update_column(:image_upload_id, nil) if @post.image_upload_id
if @post.topic.image_upload_id && @post.is_first_post?
@post.topic.update_column(:image_upload_id, nil)
end
FEATURE: Include optimized thumbnails for topics (#9215) This introduces new APIs for obtaining optimized thumbnails for topics. There are a few building blocks required for this: - Introduces new `image_upload_id` columns on the `posts` and `topics` table. This replaces the old `image_url` column, which means that thumbnails are now restricted to uploads. Hotlinked thumbnails are no longer possible. In normal use (with pull_hotlinked_images enabled), this has no noticeable impact - A migration attempts to match existing urls to upload records. If a match cannot be found then the posts will be queued for rebake - Optimized thumbnails are generated during post_process_cooked. If thumbnails are missing when serializing a topic list, then a sidekiq job is queued - Topic lists and topics now include a `thumbnails` key, which includes all the available images: ``` "thumbnails": [ { "max_width": null, "max_height": null, "url": "//example.com/original-image.png", "width": 1380, "height": 1840 }, { "max_width": 1024, "max_height": 1024, "url": "//example.com/optimized-image.png", "width": 768, "height": 1024 } ] ``` - Themes can request additional thumbnail sizes by using a modifier in their `about.json` file: ``` "modifiers": { "topic_thumbnail_sizes": [ [200, 200], [800, 800] ], ... ``` Remember that these are generated asynchronously, so your theme should include logic to fallback to other available thumbnails if your requested size has not yet been generated - Two new raw plugin outlets are introduced, to improve the customisability of the topic list. `topic-list-before-columns` and `topic-list-before-link`
2020-05-05 04:07:50 -04:00
nil
2013-07-07 19:39:08 -04:00
end
end
2013-11-05 13:04:47 -05:00
def optimize_urls
%w[href data-download-href].each do |selector|
@doc.css("a[#{selector}]").each { |a| a[selector] = UrlHelper.cook_url(a[selector].to_s) }
2013-11-05 13:04:47 -05:00
end
%w[src].each do |selector|
@doc
.css("img[#{selector}]")
.each do |img|
custom_emoji = img["class"]&.include?("emoji-custom") && Emoji.custom?(img["title"])
img[selector] = UrlHelper.cook_url(
img[selector].to_s,
secure: @post.with_secure_uploads? && !custom_emoji,
)
end
2013-11-05 13:04:47 -05:00
end
2013-02-05 14:16:51 -05:00
end
2017-10-23 13:09:38 -04:00
def remove_user_ids
@doc
.css("a[href]")
.each do |a|
uri =
begin
URI(a["href"])
rescue URI::Error
next
end
next if uri.hostname != Discourse.current_hostname
query = Rack::Utils.parse_nested_query(uri.query)
next if !query.delete("u")
uri.query = query.map { |k, v| "#{k}=#{v}" }.join("&").presence
a["href"] = uri.to_s
end
end
def enforce_nofollow
add_nofollow = !@omit_nofollow && SiteSetting.add_rel_nofollow_to_user_content
PrettyText.add_rel_attributes_to_user_content(@doc, add_nofollow)
end
2013-02-05 14:16:51 -05:00
private
def post_process_images
extract_images.each do |img|
still_an_image = process_hotlinked_image(img)
convert_to_link!(img) if still_an_image
end
end
def process_hotlinked_image(img)
@hotlinked_map ||= @post.post_hotlinked_media.preload(:upload).map { |r| [r.url, r] }.to_h
normalized_src =
PostHotlinkedMedia.normalize_src(img["src"] || img[PrettyText::BLOCKED_HOTLINKED_SRC_ATTR])
info = @hotlinked_map[normalized_src]
still_an_image = true
if info&.too_large?
if img.ancestors(".onebox, .onebox-body").blank?
add_large_image_placeholder!(img)
else
img.remove
end
still_an_image = false
elsif info&.download_failed?
if img.ancestors(".onebox, .onebox-body").blank?
add_broken_image_placeholder!(img)
else
img.remove
end
still_an_image = false
elsif info&.downloaded? && upload = info&.upload
img["src"] = UrlHelper.cook_url(upload.url, secure: @with_secure_uploads)
img.delete(PrettyText::BLOCKED_HOTLINKED_SRC_ATTR)
end
still_an_image
end
def add_blocked_hotlinked_media_placeholders
@doc
.css(
[
"[#{PrettyText::BLOCKED_HOTLINKED_SRC_ATTR}]",
"[#{PrettyText::BLOCKED_HOTLINKED_SRCSET_ATTR}]",
].join(","),
)
.each do |el|
src =
el[PrettyText::BLOCKED_HOTLINKED_SRC_ATTR] ||
el[PrettyText::BLOCKED_HOTLINKED_SRCSET_ATTR]&.split(",")&.first&.split(" ")&.first
if el.name == "img"
add_blocked_hotlinked_image_placeholder!(el)
next
end
el = el.parent if %w[video audio].include?(el.parent.name)
el = el.parent if el.parent.classes.include?("video-container")
add_blocked_hotlinked_media_placeholder!(el, src)
end
end
def is_svg?(img)
path =
begin
URI(img["src"]).path
rescue URI::Error
nil
end
File.extname(path) == ".svg" if path
end
2013-02-05 14:16:51 -05:00
end