From c0c355eff97c4b2e3e6d5f61d71b5cdf8d67a785 Mon Sep 17 00:00:00 2001
From: =?utf8?q?Paul=20H=C3=A4nsch?= <paul@plutz.net>
Date: Sun, 13 Nov 2022 22:26:12 +0100
Subject: [PATCH] Squashed 'cgilite/' changes from 6bdb2db..970afda

970afda inline image attributes, wiki style links
9a07596 bugfix/typo: correct transformation of header fields into web server variable names
5038774 escape CR and BR in HTML output (as previously specified)
e02243e table style
74f16aa bugfix: allow trailing white space in indented code
175ea96 bugfix anchor links starting with # character
dfadf30 bugfix: prevent white space lines from becoming code blocks
e619859 anchor links for headlines, bugfix: continue block processing right after tables
aa80431 Implemented pandoc grid tables
9bb2256 Implemented Pipe Tables
d1bb79c bugfix in recognition of fenced code block attributes
d09c1c1 ordered list of mime types, additional pdf and text types
cc4a446 styling classes for task list, additional task list status

git-subtree-dir: cgilite
git-subtree-split: 970afdafe1d1125607c10d3e410abae8d2244392
---
 cgilite.sh   |   4 +-
 common.css   |   8 ++-
 file.sh      |  27 ++++----
 markdown.awk | 187 +++++++++++++++++++++++++++++++++++++++++++++------
 4 files changed, 191 insertions(+), 35 deletions(-)

diff --git a/cgilite.sh b/cgilite.sh
index b47a3e2..b51ee8e 100755
--- a/cgilite.sh
+++ b/cgilite.sh
@@ -264,7 +264,7 @@ HEADER(){
     str="${str#*${BR}${1}: }"
     printf %s "${str%%${BR}*}"
   else
-    local var="HTTP_$(printf %s "$1" |tr a-z- A-Z-)"
+    local var="HTTP_$(printf %s "$1" |tr a-z- A-Z_)"
     eval "[ \"\$$var\" ] && printf %s \"\$$var\" || return 1"
     # eval "printf %s \"\$HTTP_$(printf %s "${1}" |tr a-z A-Z |tr -c A-Z _)\""
   fi
@@ -294,7 +294,7 @@ HTML(){
     \]*) out="${out}&#x5D;";      str="${str#?}";;
     "${CR}"*) out="${out}&#x0D;"; str="${str#?}";;
     "${BR}"*) out="${out}&#x0A;"; str="${str#?}";;
-    *) out="${out}${str%%[]&<>\"\'[]*}"; str="${str#"${str%%[]&<>\"\'[]*}"}";;
+    *) out="${out}${str%%[]&<>\"\'${CR}${BR}[]*}"; str="${str#"${str%%[]&<>\"\'${CR}${BR}[]*}"}";;
   esac; done
   printf %s "$out"
 }
diff --git a/common.css b/common.css
index c5cf6c4..65c28f3 100644
--- a/common.css
+++ b/common.css
@@ -16,9 +16,15 @@ body {
   color: #000; background: #FFF;
 }
 
-ul, ol, dl, table, p { margin-bottom: .5em; }
+ul, ol, dl, table, pre, p { margin-bottom: .5em; }
 p:only-child { margin-bottom: 0; }
 
+table {
+  max-width: 100%;
+  overflow-x: auto;
+}
+th, td { padding: .25em .75em; }
+
 a {
   font-style: italic;
   text-decoration: underline;
diff --git a/file.sh b/file.sh
index 6f956df..0d1f4ea 100755
--- a/file.sh
+++ b/file.sh
@@ -22,24 +22,27 @@ include_fileserve="$0"
 
 file_type(){
   case ${1##*.} in
-    html|html) printf 'text/html';;
     css)       printf 'text/css';;
-    js)        printf 'text/javascript';;
-    txt)       printf 'text/plain';;
-    sh)        printf 'text/shellscript';;
+    gif)       printf 'image/gif';;
+    html|html) printf 'text/html';;
     jpg|jpeg)  printf 'image/jpeg';;
+    js)        printf 'text/javascript';;
+    m3u8)      printf 'application/x-mpegURL';;
+    m4a)       printf 'audio/mp4';;
+    m4s)       printf 'video/iso.segment';;
+    m4v|mp4)   printf 'video/mp4';;
+    mpd)       printf 'application/dash+xml';;
+    ogg)       printf 'audio/ogg';;
+    pdf)       printf 'application/pdf';;
     png)       printf 'image/png';;
+    sh)        printf 'text/x-shellscript';;
     svg)       printf 'image/svg+xml';;
-    gif)       printf 'image/gif';;
+    tex)       printf 'text/x-tex';;
+    txt)       printf 'text/plain';;
+    short)     printf 'text/prs.shorthand';;
+    ts)        printf 'video/MP2T';;
     webm)      printf 'video/webm';;
-    mp4|m4v)   printf 'video/mp4';;
-    m4a)       printf 'audio/mp4';;
-    ogg)       printf 'audio/ogg';;
     xml)       printf 'application/xml';;
-    m3u8)      printf 'application/x-mpegURL';;
-    ts)        printf 'video/MP2T';;
-    mpd)       printf 'application/dash+xml';;
-    m4s)       printf 'video/iso.segment';;
     *)         printf 'application/octet-stream';;
   esac
 }
diff --git a/markdown.awk b/markdown.awk
index e63541b..44d4e0d 100755
--- a/markdown.awk
+++ b/markdown.awk
@@ -42,13 +42,13 @@
 # - [x] Automatic heading identifiers (custom)
 # - [x] Fenced code blocks (php md, pandoc)
 #   - [x] Fenced code attributes
-# - [ ] Tables
+# - [/] Tables
 #   -  ?  Simple table (pandoc)
 #   -  ?  Multiline table (pandoc)
-#   -  ?  Grid table (pandoc)
-#   -  ?  Pipe table (php md pandoc)
+#   - [x] Grid table (pandoc)
+#   - [x] Pipe table (php md pandoc)
 # - [x] Line blocks (pandoc)
-# - [x] Task lists (pandoc)
+# - [x] Task lists (pandoc, custom)
 # - [ ] Definition lists (php md, pandoc)
 # - [-] Numbered example lists (pandoc)
 # - [-] Metadata blocks (pandoc)
@@ -62,6 +62,8 @@
 # - [x] ^Superscript^ ~Subscript~ (pandoc)
 # - [-] Bracketed spans (pandoc)
 #   - [-] Inline attributes (pandoc)
+# - [x] Image attributes (custom, pandoc inspired, inline only)
+# - [x] Wiki style links [[PageName]] / [[PageName|Link Text]]
 # - [-] TEX-Math (pandoc)
 # -  ?  Footnotes (php md)
 # -  ?  Abbreviations (php md)
@@ -117,6 +119,14 @@ function inline( line, LOCAL, len, code, href, guard ) {
       return "<code>" code "</code>" inline( substr( line, len + 1 ) )
     }
 
+  # Wiki style links
+  } else if ( match( line, /^\[\[([^\]\|]+)(\|([^\]]+))?\]\]/) ) {
+    len = RLENGTH;
+    href = gensub(/^\[\[([^\]\|]+)(\|([^\]]+))?\]\]/, "\\1", 1, substr(line, 1, len) );
+    text = gensub(/^\[\[([^\]\|]+)(\|([^\]]+))?\]\]/, "\\3", 1, substr(line, 1, len) );
+    if ( ! text ) text = href;
+    return "<a href=\"" HTML(href) "\">" HTML(text) "</a>" inline( substr( line, len + 1) );
+
   #  quick links ("automatic links" in md doc)
   } else if ( match( line, /^<[a-zA-Z]+:\/\/([-\.[:alnum:]]+)(:[0-9]*)?(\/[^>]*)?>/ ) ) {
     len = RLENGTH;
@@ -156,13 +166,18 @@ function inline( line, LOCAL, len, code, href, guard ) {
     }
 
   # inline images
-  } else if ( match(line, /^!\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)/) ) {
+  } else if ( match(line, /^!\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)(\{([a-zA-Z \t-]*)\})?/) ) {
     len = RLENGTH;
-    text  = gensub(/^!\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)/, "\\1", "g", substr(line, 1, len) );
-    href  = gensub(/^!\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)/, "\\2", "g", substr(line, 1, len) );
-    title = gensub(/^!\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)/, "\\4", "g", substr(line, 1, len) );
-    if ( title ) {
+    text   = gensub(/^!\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)(\{([a-zA-Z \t-]*)\})?/, "\\1", "g", substr(line, 1, len) );
+    href   = gensub(/^!\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)(\{([a-zA-Z \t-]*)\})?/, "\\2", "g", substr(line, 1, len) );
+    title  = gensub(/^!\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)(\{([a-zA-Z \t-]*)\})?/, "\\4", "g", substr(line, 1, len) );
+    attrib = gensub(/^!\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)(\{([a-zA-Z \t-]*)\})?/, "\\6", "g", substr(line, 1, len) );
+    if ( title && attrib ) {
+      return "<img src=\"" HTML(href) "\" alt=\"" HTML(text) "\" title=\"" HTML(title) "\" class=\"" HTML(attrib) "\"/>" inline( substr( line, len + 1) );
+    } else if ( title ) {
       return "<img src=\"" HTML(href) "\" alt=\"" HTML(text) "\" title=\"" HTML(title) "\" />" inline( substr( line, len + 1) );
+    } else if ( attrib ) {
+      return "<img src=\"" HTML(href) "\" alt=\"" HTML(text) "\" class=\"" HTML(attrib) "\" />" inline( substr( line, len + 1) );
     } else {
       return "<img src=\"" HTML(href) "\" alt=\"" HTML(text) "\" />" inline( substr( line, len + 1) );
     }
@@ -296,6 +311,115 @@ function _block( block, LOCAL, st, len, hlvl, htxt, guard, code, indent, attrib
     return "<blockquote>\n" _block( gensub( /(^|\n)> /, "\n", "g", substr(block, 1, st - 1) ) ) "</blockquote>\n\n" \
            _block( substr(block, st + len) );
 
+  # Pipe Tables (pandoc / php md / gfm )
+  } else if ( match(block, "^((\\|)?([^\n]+\\|)+[^\n]+(\\|)?)\n" \
+                           "((\\|)?:?(-+:?[\\|+])+:?-+:?(\\|)?)\n" \
+                           "((\\|)?([^\n]+\\|)+[^\n]+(\\|)?(\n|$))+" ) ) {
+    len = RLENGTH; st = RSTART;
+    #initialize empty arrays
+    split("", talign); split("", tarray);
+    cols = 0; cnt=0; ttext = "";
+
+    # table header and alignment
+    split( gensub( /(^\||\|$)/, "", "g", \
+           gensub( /(^|[^\\])\\\|/, "\\1\\&#x7C;", "g", \
+           substr(block, 1, match(block, /(\n|$)/)) \
+    )), tarray, /\|/);
+    block = substr(block, match(block, /(\n|$)/) + 1 );
+    cols = split( \
+           gensub( /(^\||\|$)/, "", "g", \
+           substr(block, 1, match(block, /(\n|$)/)) \
+    ), talign, /[+\|]/);
+    block = substr(block, match(block, /(\n|$)/) + 1 );
+
+    for( cnt = 1; cnt < cols; cnt++ ) {
+           if (match(talign[cnt], /:-+:/)) talign[cnt]="center";
+      else if (match(talign[cnt],  /-+:/)) talign[cnt]="right";
+      else if (match(talign[cnt],  /:-+/)) talign[cnt]="left";
+      else talign[cnt]="";
+    }
+
+    ttext = "<thead>\n<tr>"
+    for (cnt = 1; cnt < cols; cnt++)
+      ttext = ttext "<th align=\"" talign[cnt] "\">" inline(tarray[cnt]) "</th>"
+    ttext = ttext "</tr>\n</thead><tbody>\n"
+
+    while ( match(block, "^((\\|)?([^\n]+\\|)+[^\n]+(\\|)?(\n|$))+" ) ){
+      split( gensub( /(^\||\|$)/, "", "g", \
+             gensub( /(^|[^\\])\\\|/, "\\1\\&#x7C;", "g", \
+             substr(block, 1, match(block, /(\n|$)/)) \
+      )), tarray, /\|/);
+      block = substr(block, match(block, /(\n|$)/) + 1 );
+
+      ttext = ttext "<tr>"
+      for (cnt = 1; cnt < cols; cnt++)
+        ttext = ttext "<td align=\"" talign[cnt] "\">" inline(tarray[cnt]) "</td>"
+      ttext = ttext "</tr>\n"
+    }
+    return "<table>" ttext "</tbody></table>\n" _block(block);
+
+  # Grid Tables (pandoc)
+  } else if ( match(block, "^\\+(-+\\+)+\n" \
+                       "(\\|([^\n]+\\|)+\n)+" \
+                        "\\+(:?=+:?\\+)+\n" \
+                      "((\\|([^\n]+\\|)+\n)+" \
+                            "\\+(-+\\+)+(\n|$))+" \
+            ) ) {
+    len = RLENGTH; st = RSTART;
+    #initialize empty arrays
+    split("", talign); split("", tarray); split("", tread);
+    cols = 0; cnt=0; ttext = "";
+
+    # table header and alignment
+    block = substr(block, match(block, /(\n|$)/) + 1 );
+    while ( match(block, "^\\|([^\n]+\\|)+\n") ) {
+      cols = split( gensub( /(^\||\|$)/, "", "g", \
+             gensub( /(^|[^\\])\\\|/, "\\1\\&#x7C;", "g", \
+             substr(block, 1, match(block, /(\n|$)/)) \
+      )), tread, /\|/);
+      block = substr(block, match(block, /(\n|$)/) + 1 );
+      for (cnt = 1; cnt < cols; cnt++)
+        tarray[cnt] = tarray[cnt] "\n" tread[cnt];
+    }
+
+    cols = split( \
+           gensub( /(^\+|\+$)/, "", "g", \
+           substr(block, 1, match(block, /(\n|$)/)) \
+    ), talign, /\+/);
+    block = substr(block, match(block, /(\n|$)/) + 1 );
+
+    for (cnt = 1; cnt < cols; cnt++) {
+           if (match(talign[cnt], /:=+:/)) talign[cnt]="center";
+      else if (match(talign[cnt],  /=+:/)) talign[cnt]="right";
+      else if (match(talign[cnt], /:=+/ )) talign[cnt]="left";
+      else talign[cnt]="";
+    }
+
+    ttext = "<thead>\n<tr>"
+    for (cnt = 1; cnt < cols; cnt++)
+      ttext = ttext "<th align=\"" talign[cnt] "\">" _block(tarray[cnt]) "</th>"
+    ttext = ttext "</tr>\n</thead><tbody>\n"
+
+    while ( match(block, /^((\|([^\n]+\|)+\n)+\+(-+\+)+(\n|$))+/ ) ){
+      split("", tarray);
+      while ( match(block, /^\|([^\n]+\|)+\n/) ) {
+        split( gensub( /(^\||\|$)/, "", "g", \
+               gensub( /(^|[^\\])\\\|/, "\\1\\&#x7C;", "g", \
+               substr(block, 1, match(block, /(\n|$)/)) \
+        )), tread, /\|/);
+        block = substr(block, match(block, /(\n|$)/) + 1 );
+        for (cnt = 1; cnt < cols; cnt++)
+          tarray[cnt] = tarray[cnt] "\n" tread[cnt];
+      }
+      block = substr(block, match(block, /(\n|$)/) + 1 );
+
+      ttext = ttext "<tr>"
+      for (cnt = 1; cnt < cols; cnt++)
+        ttext = ttext "<td align=\"" talign[cnt] "\">" _block(tarray[cnt]) "</td>"
+      ttext = ttext "</tr>\n"
+    }
+    return "<table>" ttext "</tbody></table>\n" _block(block);
+
   # Line Blocks (pandoc)
   } else if ( match(block, /^\| [^\n]*(\n|$)(\| [^\n]*(\n|$)|[ \t]+[^\n[:space:]][^\n]*(\n|$))*/) ) {
     len = RLENGTH; st = RSTART;
@@ -307,7 +431,7 @@ function _block( block, LOCAL, st, len, hlvl, htxt, guard, code, indent, attrib
            _block( substr( block, len + 1) );
 
   # Indented Code Block
-  } else if ( match(block, /^(    |\t)[^\n]+(\n|$)((    |\t)[^\n]+(\n|$)|[ \t]*(\n|$))*/) ) {
+  } else if ( match(block, /^(    |\t)( *\t*[^ \t\n]+ *\t*)+(\n|$)((    |\t)[^\n]+(\n|$)|[ \t]*(\n|$))*/) ) {
     len = RLENGTH; st = RSTART;
     code = substr(block, 1, len);
     gsub(/(^|\n)(    |\t)/, "\n", code);
@@ -337,7 +461,7 @@ function _block( block, LOCAL, st, len, hlvl, htxt, guard, code, indent, attrib
   } else if ( match( block, /^(~~~+|```+)/ ) ) {
     guard = substr( block, 1, RLENGTH );
     code = gensub(/^[^\n]+\n/, "", 1, block);
-    attrib = gensub(/^:::+[ \t]*\{?[ \t]*([^\}\n]*)\}?[ \t]*\n.*$/, "\\1", 1, block);
+    attrib = gensub(/^(~~~+|```+)[ \t]*\{?[ \t]*([^\}\n]*)\}?[ \t]*\n.*$/, "\\2", 1, block);
     gsub(/[^a-zA-Z0-9_-]+/, " ", attrib);
     gsub(/(^ | $)/, "", attrib);
     if ( match(code, "(^|\n)" guard "+(\n|$)" ) ) {
@@ -379,14 +503,20 @@ function _block( block, LOCAL, st, len, hlvl, htxt, guard, code, indent, attrib
   } else if ( match( block, /^[^\n]+\n===+(\n|$)/ ) ) {
     len = RLENGTH;
     HL[1]++; HL[2] = 0; HL[3] = 0; HL[4] = 0; HL[5] = 0; HL[6] = 0;
-    return "<h1 id=\"" HL[1] " - " HTML(gensub( /\n.*$/, "", "g", block )) "\">" inline( gensub( /\n.*$/, "", "g", block ) ) "</h1>\n\n" \
+    return "<h1 id=\"" HL[1] " - " HTML(gensub( /\n.*$/, "", "g", block )) "\">" \
+           inline( gensub( /\n.*$/, "", "g", block ) ) \
+           "<a class=\"anchor\" href=\"#" HL[1] " - " \
+           HTML(gensub( /\n.*$/, "", "g", block )) "\"></a></h1>\n\n" \
            _block( substr( block, len + 1 ) );
 
   # Second Order Heading
   } else if ( match( block, /^[^\n]+\n---+(\n|$)/ ) ) {
     len = RLENGTH;
     HL[2]++; HL[3] = 0; HL[4] = 0; HL[5] = 0; HL[6] = 0;
-    return "<h2 id=\"" HL[1] "." HL[2] " - " HTML(gensub( /\n.*$/, "", "g", block )) "\">" inline( gensub( /\n.*$/, "", "g", block ) ) "</h2>\n\n" \
+    return "<h2 id=\"" HL[1] "." HL[2] " - " HTML(gensub( /\n.*$/, "", "g", block )) "\">" \
+           inline( gensub( /\n.*$/, "", "g", block ) ) \
+           "<a class=\"anchor\" href=\"#" HL[1] "." HL[2] " - " \
+           HTML(gensub( /\n.*$/, "", "g", block )) "\"></a></h2>\n\n" \
            _block( substr( block, len + 1) );
 
   # Nth Order Heading
@@ -396,7 +526,8 @@ function _block( block, LOCAL, st, len, hlvl, htxt, guard, code, indent, attrib
     htxt = gensub(/^#{1,6}[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[^\n#])+)([ \t]*#*)(\n.*)?$/, "\\1", 1, block);
     HL[hlvl]++; for ( n = hlvl + 1; n < 7; n++) { HL[n] = 0;}
     hid = HL[1]; for ( n = 2; n <= hlvl; n++) { hid = hid "." HL[n] ; }
-    return "<h" hlvl " id=\"" hid " - " HTML(htxt) "\">" inline( htxt ) "</h" hlvl ">\n\n" \
+    return "<h" hlvl " id=\"" hid " - " HTML(htxt) "\">" inline( htxt ) \
+           "<a class=\"anchor\" href=\"#" hid "\"></a></h" hlvl ">\n\n" \
            _block( substr( block, len + 1) );
 
   # Split paragraphs
@@ -440,12 +571,28 @@ function _list( block, last, LOCAL, p) {
   }
   sub( /\n$/, "", p );
 
-  # Task List (pandoc)
-       if ( p ~ /^\[ \].*/ )       { p = "<input type=checkbox disabled />" substr(p, 4); }
-  else if ( p ~ /^\[[xX]\].*/ )    { p = "<input type=checkbox disabled checked />" substr(p, 4); }
-  else if ( p ~ /^<p>\[ \].*/ )    { p = "<p><input type=checkbox disabled />" substr(p, 7); }
-  else if ( p ~ /^<p>\[[xX]\].*/ ) { p = "<p><input type=checkbox disabled checked />" substr(p, 7); }
-  return "<li>" p "</li>\n" _list( block, last );
+  # Task List (pandoc, custom)
+         if ( p ~ /^\[ \].*/ )       { return "<li class=\"task pending\"><input type=checkbox disabled />" \
+                                              substr(p, 4) "</li>\n" _list( block, last );
+  } else if ( p ~ /^\[-\].*/ )       { return "<li class=\"task negative\"><input type=checkbox disabled />" \
+                                              substr(p, 4) "</li>\n" _list( block, last );
+  } else if ( p ~ /^\[\?\].*/ )      { return "<li class=\"task unsure\"><input type=checkbox disabled />" \
+                                              substr(p, 4) "</li>\n" _list( block, last );
+  } else if ( p ~ /^\[\/\].*/ )      { return "<li class=\"task partial\"><input type=checkbox disabled />" \
+                                              substr(p, 4) "</li>\n" _list( block, last );
+  } else if ( p ~ /^\[[xX]\].*/ )    { return "<li class=\"task done\"><input type=checkbox disabled checked />" \
+                                            substr(p, 4) "</li>\n" _list( block, last );
+  } else if ( p ~ /^<p>\[ \].*/ )    { return "<li class=\"task pending\"><p><input type=checkbox disabled />" \
+                                              substr(p, 7) "</li>\n" _list( block, last );
+  } else if ( p ~ /^<p>\[-\].*/ )    { return "<li class=\"task negative\"><p><input type=checkbox disabled />" \
+                                              substr(p, 7) "</li>\n" _list( block, last );
+  } else if ( p ~ /^<p>\[\?\].*/ )   { return "<li class=\"task unsure\"><p><input type=checkbox disabled />" \
+                                              substr(p, 7) "</li>\n" _list( block, last );
+  } else if ( p ~ /^<p>\[\/\].*/ )   { return "<li class=\"task partial\"><p><input type=checkbox disabled />" \
+                                              substr(p, 7) "</li>\n" _list( block, last );
+  } else if ( p ~ /^<p>\[[xX]\].*/ ) { return "<li class=\"task done\"><p><input type=checkbox disabled checked />" \
+                                              substr(p, 7) "</li>\n" _list( block, last );
+  } else { return "<li>" p "</li>\n" _list( block, last ); }
 }
 
 BEGIN {
-- 
2.39.2