From 0ca931489f98b65e1025a4c4f00ae9eb8484dc27 Mon Sep 17 00:00:00 2001
From: B Stack <bgstack15@gmail.com>
Date: Tue, 16 Jun 2020 13:40:39 -0400
Subject: add minor fixes and major image fixes

   perform better unicode removal/conversion
   fix image retrieval, including svg and minor graphics assets
   remove even more html elements not necessary for archival display
---
 flow.md | 22 +++++++++++++++-------
 1 file changed, 15 insertions(+), 7 deletions(-)

(limited to 'flow.md')

diff --git a/flow.md b/flow.md
index 5c81d5e..ca81d52 100644
--- a/flow.md
+++ b/flow.md
@@ -24,27 +24,27 @@ Everything on this page, for jq filtering. https://stedolan.github.io/jq/manual/
 
   * fix newlines
 
-    sed -i -r -e 's/\\n/\n/g;' /mnt/public/www/issues/*.html
+    sed -i -r -e 's/\\n/\n/g;' /mnt/public/www/gitlab-issues/*.html
 
   * find data-original-titles and replace the <time> tag contents with the value of its data-original-title. Also, this will BeautifulSoup pretty-print the html so some of the following commands work correctly.
 
-    ls -1 /mnt/public/www/issues/*.html > output/files-for-timestamps.txt
+    ls -1 /mnt/public/www/gitlab-issues/*.html > output/files-for-timestamps.txt
     ./fix-timestamps.py
 
   * download all relevant images, and then fix them.
 
     ./fetch-images.sh
-    sed -i -f fix-images-in-html.sed /mnt/public/www/issues/*.html
+    sed -i -f fix-images-in-html.sed /mnt/public/www/gitlab-issues/*.html
 
   * download all stylesheets and then fix them.
 
-    mkdir -p /mnt/public/www/issues/css
+    mkdir -p /mnt/public/www/gitlab-issues/css
     ./fetch-css.sh
-    sed -i -f fix-css-in-html.sed /mnt/public/www/issues/*.html
+    sed -i -f fix-css-in-html.sed /mnt/public/www/gitlab-issues/*.html
 
   * fix some encoding oddities
 
-    sed -i -f remove-useless.sed /mnt/public/www/issues/*.html
+    sed -i -f remove-useless.sed /mnt/public/www/gitlab-issues/*.html
 
   * remove html components that are not necessary
 
@@ -52,6 +52,14 @@ Everything on this page, for jq filtering. https://stedolan.github.io/jq/manual/
 
   * Fix links that point to defunct domain without-systemd.org.
 
-    sed -i -r -f fix-without-systemd-links.sed /mnt/public/www/issues/*.html
+    sed -i -r -f fix-without-systemd-links.sed /mnt/public/www/gitlab-issues/*.html
+
+  * Perform final encoding conversion to remove any remaining broken characters
+
+    ./conversion.sh /mnt/public/www/gitlab-issues/*.html
+
+  * Fix some images that have a src="data:" that do not load, but the data-src property is the proper link
+
+    ./use-datasrc-instead-src.py
 
   * build some sort of index?
-- 
cgit