Improve index generation

Makefile

@@ -64,10 +64,17 @@ indexcache: $(DST_XML_FILES)
 ALL += indexcache
 
 # HTML INDEX
+DST_INDEX_FILES ?= $(patsubst %.xml,%.index, $(DST_XML_FILES))
+MK_INDEX_ENTRY := ./engine/mk-index-entry.sh
+INDEX_CACHE_DIR ?= $(CACHE_DIR)/rss
+$(INDEX_CACHE_DIR)/%.index: $(INDEX_CACHE_DIR)/%.xml $(MK_INDEX_ENTRY)
+	@mkdir -p $(INDEX_CACHE_DIR)
+	$(MK_INDEX_ENTRY) "$<" "$@"
+
 HTML_INDEX := $(DST_DIR)/index.html
 MKINDEX := engine/mk-index.sh
 INDEX_TEMPLATE ?= templates/index.html
-$(HTML_INDEX): $(DST_XML_FILES) $(MKINDEX) $(INDEX_TEMPLATE)
+$(HTML_INDEX): $(DST_INDEX_FILES) $(MKINDEX) $(INDEX_TEMPLATE)
 	@mkdir -p $(DST_DIR)
 	$(MKINDEX)
 .PHONY: index
@@ -85,10 +92,9 @@ RSS := $(DST_DIR)/rss.xml
 MKRSS := engine/mkrss.sh
 $(RSS): $(DST_RSS_FILES) $(MKRSS)
 	$(MKRSS)
-ALL += $(RSS)
 
 .PHONY: rss
-rss: $(DST_RSS_FILES) $(RSS)
+rss: $(RSS)
 ALL += rss
 
 

engine/mk-index-entry.sh

@@ -0,0 +1,57 @@
+#!/usr/bin/env zsh
+
+cd "$(git rev-parse --show-toplevel)" || exit 1
+
+xfic="$1"
+dst="$2"
+
+# Directory
+webdir="_site"
+postsdir="$webdir/posts"
+indexdir=".cache/rss"
+
+# HTML Accessors (similar to CSS accessors)
+dateaccessor='.yyydate'
+# title and keyword shouldn't be changed
+titleaccessor='title'
+keywordsaccessor='meta[name=keywords]::attr(content)'
+
+formatdate() {
+    # format the date for RSS
+    local d="$1"
+    # echo "DEBUG DATE: $d" >&2
+    LC_TIME=en_US date --date $d +'%a, %d %b %Y %H:%M:%S %z'
+}
+finddate(){ < $1 hxselect -c $dateaccessor | sed 's/\[//g;s/\]//g;s/ .*$//' }
+findtitle(){ < $1 hxselect -c $titleaccessor }
+findkeywords(){ < $1 hxselect -c $keywordsaccessor | sed 's/,/ /g' }
+mktaglist(){
+    for keyword in $*; do
+        printf "<span class=\"tag\">%s</span>" $keyword
+    done | sed 's#><#>, <#g'
+}
+
+autoload -U colors && colors
+
+postfile="$(echo "$xfic"|sed 's#^'$postsdir'/##')"
+blogfile="$(echo "$xfic"|sed 's#.xml$#.html#;s#^'$indexdir'/#posts/#')"
+printf "%-30s" $blogfile
+d=$(finddate $xfic)
+echo -n " [$d]"
+rssdate=$(formatdate $d)
+title=$(findtitle $xfic)
+keywords=( $(findkeywords $xfic) )
+printf ": %-55s" "$title ($keywords)"
+taglist=$(mktaglist $keywords)
+{ printf "\\n<li>"
+  printf "\\n<span class=\"pubDate\">%s</span>" "$d"
+  printf "\\n<a href=\"%s\">%s</a>" "${blogfile}" "$title"
+  printf "\\n</li>\\n\\n"
+} >> ${dst}.tmp
+
+# overwrite only if the value in the index are different
+if ! cmp -s ${dst} ${dst}.tmp; then
+  echo " [${fg[yellow]}M${reset_color}]"
+  mv -f ${dst}.tmp ${dst}
+fi
+echo " [${fg[green]}OK${reset_color}]"

engine/mk-index.sh

@@ -33,36 +33,27 @@ mktaglist(){
 
 autoload -U colors && colors
 tmpdir=$(mktemp -d)
-typeset -a dates
-dates=( )
-for xfic in $indexdir/**/*.xml; do
-    postfile="$(echo "$xfic"|sed 's#^'$postsdir'/##')"
-    blogfile="$(echo "$xfic"|sed 's#.xml$#.html#;s#^'$indexdir'/#posts/#')"
-    printf "%-30s" $postfile
-    d=$(finddate $xfic)
-    echo -n " [$d]"
-    rssdate=$(formatdate $d)
-    title=$(findtitle $xfic)
-    keywords=( $(findkeywords $xfic) )
-    printf ": %-55s" "$title ($keywords)"
-    taglist=$(mktaglist $keywords)
-    { printf "\\n<li>"
-      printf "\\n<span class=\"pubDate\">%s</span>" "$d"
-      printf "\\n<a href=\"%s\">%s</a>" "${blogfile}" "$title"
-      printf "\\n</li>\\n\\n"
-    } >>  "$tmpdir/${d}-$(basename $xfic).index"
-    dates=( $d $dates )
-    echo " [${fg[green]}OK${reset_color}]"
-done
 
 echo "Publishing"
 
 # building the body
 
+
+dateaccessor='.pubDate'
+finddate(){ < $1 hxselect -c $dateaccessor }
+
 previousyear=""
-for fic in $(ls $tmpdir/*.index | sort -r | head -n $maxarticles ); do
+for fic in $indexdir/**/*.index; do
+    d=$(finddate $fic)
+    echo "${${fic:h}:t} [$d]"
+    cp $fic $tmpdir/$d-${${fic:h}:t}.index
+done
+
+previousyear=""
+for fic in $(ls $tmpdir/*.index | sort -r); do
+    d=$(finddate $fic)
     echo "${fic:t}"
-    year=$( echo "${fic:t}" | perl -pe 's#(\d{4})-.*#$1#')
+    year=$( echo "$d" | perl -pe 's#(\d{4})-.*#$1#')
     if (( year != previousyear )); then
         echo $year
         if (( previousyear > 0 )); then

engine/mk-rss-entry.sh

@@ -45,7 +45,7 @@ autoload -U colors && colors
 xfic="$fic"
 postfile="$(echo "$fic"|sed 's#^'$postsdir'/##')"
 blogfile="$(echo "$fic"|sed 's#.xml$#.html#;s#^'$indexdir'/#posts/#')"
-printf "%-30s" $postfile
+printf "%-30s" $blogfile
 d=$(finddate $xfic)
 echo -n " [$d]"
 rssdate=$(formatdate $d)
@@ -54,7 +54,7 @@ keywords=( $(findkeywords $xfic) )
 printf ": %-55s" "$title ($keywords)"
 categories=$(mkcategories $keywords)
 absoluteurl="${websiteurl}/${blogfile}"
-mkdir -p $(dirname $dst)
+[[ ! -d $(dirname $dst) ]] && mkdir -p $(dirname $dst)
 { printf "\\n<item>"
   printf "\\n<title>%s</title>" "$title"
   printf "\\n<guid>%s</guid>" "$absoluteurl"
@@ -63,8 +63,10 @@ mkdir -p $(dirname $dst)
   printf "\\n<description><![CDATA[\\n%s\\n]]></description>" "$(getcontent "$xfic" "$absoluteurl")"
   printf "\\n</item>\\n\\n"
 } >  "${dst}.tmp"
+
 # overwrite only if the value in the index are different
 if ! cmp -s ${dst} ${dst}.tmp; then
+  echo " [${fg[yellow]}M${reset_color}]"
   mv -f ${dst}.tmp ${dst}
 fi
 echo " [${fg[green]}OK${reset_color}]"

engine/mkrss.sh

@@ -32,7 +32,7 @@ formatdate() {
 isodate() {
     # format the date for sorting
     local d="$1"
-    echo "DEBUG DATE: $d" >&2
+    # echo "DEBUG DATE: $d" >&2
     LC_TIME=en_US date --date "$d" +'%Y-%m-%dT%H:%M:%S'
 }
 
@@ -45,7 +45,7 @@ dates=( )
 tmpdir=$(mktemp -d)
 for fic in $indexdir/**/*.rss; do
     rssdate=$(finddate $fic)
-    echo -n "${fic:r} [$d]"
+    echo -n "${${fic:h}:t} [$rssdate]"
     d=$(isodate $rssdate)
     dates=( $d $dates )
     echo " [${fg[green]}OK${reset_color}]"

src/posts/0018-makefile-as-static-site-builder-follow-up/index.org

@@ -308,6 +308,7 @@ ALL += indexcache
 So to resume this rule will generate for every file in =site/posts/*.html=
 a corresponding =xml= file (=hxclean= takes an HTML an try its best to make
 an XML out of it).
+
 ** HTML Index
 :PROPERTIES:
 :CUSTOM_ID: html-index
@@ -335,6 +336,11 @@ My =mk-index.sh= script takes advantage of the index files we constructed
 before with =hxclean=.
 Mainly I use =hxselect= to find the information I want to find, the
 title, the date and the keywords.
+So my script is composed of three parts:
+
+1. declare the accessors (think CSS-like accessor)
+2. for all files in the cache retrieve the metas, and sort them by date
+3. compose the content
 
 #+begin_src bash
 #!/usr/bin/env zsh