From 5746cba860e5a30cd05dd46ccc3dac9ba2c88ded Mon Sep 17 00:00:00 2001 From: David Malcolm Date: Tue, 8 Sep 2015 10:24:53 -0400 Subject: [PATCH 01/26] FIXME: add ansi2html.sh for now --- ansi2html.sh | 493 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 493 insertions(+) create mode 100755 ansi2html.sh diff --git a/ansi2html.sh b/ansi2html.sh new file mode 100755 index 0000000..c93899c --- /dev/null +++ b/ansi2html.sh @@ -0,0 +1,493 @@ +#!/bin/sh + +# Convert ANSI (terminal) colours and attributes to HTML + +# Licence: LGPLv2 +# Author: +# http://www.pixelbeat.org/docs/terminal_colours/ +# Examples: +# ls -l --color=always | ansi2html.sh > ls.html +# git show --color | ansi2html.sh > last_change.html +# Generally one can use the `script` util to capture full terminal output. +# Changes: +# V0.1, 24 Apr 2008, Initial release +# V0.2, 01 Jan 2009, Phil Harnish +# Support `git diff --color` output by +# matching ANSI codes that specify only +# bold or background colour. +# P@draigBrady.com +# Support `ls --color` output by stripping +# redundant leading 0s from ANSI codes. +# Support `grep --color=always` by stripping +# unhandled ANSI codes (specifically ^[[K). +# V0.3, 20 Mar 2009, http://eexpress.blog.ubuntu.org.cn/ +# Remove cat -v usage which mangled non ascii input. +# Cleanup regular expressions used. +# Support other attributes like reverse, ... +# P@draigBrady.com +# Correctly nest tags (even across lines). +# Add a command line option to use a dark background. +# Strip more terminal control codes. +# V0.4, 17 Sep 2009, P@draigBrady.com +# Handle codes with combined attributes and color. +# Handle isolated attributes with css. +# Strip more terminal control codes. +# V0.21, 26 Jan 2015 +# http://github.com/pixelb/scripts/commits/master/scripts/ansi2html.sh + +gawk --version >/dev/null || exit 1 + +if [ "$1" = "--version" ]; then + printf '0.21\n' && exit +fi + +if [ "$1" = "--help" ]; then + printf '%s\n' \ +'This utility converts ANSI codes in data passed to stdin +It has 2 optional parameters: + --bg=dark --palette=linux|solarized|tango|xterm +E.g.: ls -l --color=always | ansi2html.sh --bg=dark > ls.html' >&2 + exit +fi + +[ "$1" = "--bg=dark" ] && { dark_bg=yes; shift; } + +if [ "$1" = "--palette=solarized" ]; then + # See http://ethanschoonover.com/solarized + P0=073642; P1=D30102; P2=859900; P3=B58900; + P4=268BD2; P5=D33682; P6=2AA198; P7=EEE8D5; + P8=002B36; P9=CB4B16; P10=586E75; P11=657B83; + P12=839496; P13=6C71C4; P14=93A1A1; P15=FDF6E3; + shift; +elif [ "$1" = "--palette=solarized-xterm" ]; then + # Above mapped onto the xterm 256 color palette + P0=262626; P1=AF0000; P2=5F8700; P3=AF8700; + P4=0087FF; P5=AF005F; P6=00AFAF; P7=E4E4E4; + P8=1C1C1C; P9=D75F00; P10=585858; P11=626262; + P12=808080; P13=5F5FAF; P14=8A8A8A; P15=FFFFD7; + shift; +elif [ "$1" = "--palette=tango" ]; then + # Gnome default + P0=000000; P1=CC0000; P2=4E9A06; P3=C4A000; + P4=3465A4; P5=75507B; P6=06989A; P7=D3D7CF; + P8=555753; P9=EF2929; P10=8AE234; P11=FCE94F; + P12=729FCF; P13=AD7FA8; P14=34E2E2; P15=EEEEEC; + shift; +elif [ "$1" = "--palette=xterm" ]; then + P0=000000; P1=CD0000; P2=00CD00; P3=CDCD00; + P4=0000EE; P5=CD00CD; P6=00CDCD; P7=E5E5E5; + P8=7F7F7F; P9=FF0000; P10=00FF00; P11=FFFF00; + P12=5C5CFF; P13=FF00FF; P14=00FFFF; P15=FFFFFF; + shift; +else # linux console + P0=000000; P1=AA0000; P2=00AA00; P3=AA5500; + P4=0000AA; P5=AA00AA; P6=00AAAA; P7=AAAAAA; + P8=555555; P9=FF5555; P10=55FF55; P11=FFFF55; + P12=5555FF; P13=FF55FF; P14=55FFFF; P15=FFFFFF; + [ "$1" = "--palette=linux" ] && shift +fi + +[ "$1" = "--bg=dark" ] && { dark_bg=yes; shift; } + +# Mac OSX's GNU sed is installed as gsed +# use e.g. homebrew 'gnu-sed' to get it +if ! sed --version >/dev/null 2>&1; then + if gsed --version >/dev/null 2>&1; then + alias sed=gsed + else + echo "Error, can't find an acceptable GNU sed." >&2 + exit 1 + fi +fi + +printf '%s' " + + + + + + +
+'
+
+p='\x1b\['        #shortcut to match escape codes
+
+# Handle various xterm control sequences.
+# See /usr/share/doc/xterm-*/ctlseqs.txt
+sed "
+# escape ampersand and quote
+s#&#\&#g; s#\"#\"#g;
+s#\x1b[^\x1b]*\x1b\\\##g  # strip anything between \e and ST
+s#\x1b][0-9]*;[^\a]*\a##g # strip any OSC (xterm title etc.)
+
+s#\r\$## # strip trailing \r
+
+# strip other non SGR escape sequences
+s#[\x07]##g
+s#\x1b[]>=\][0-9;]*##g
+s#\x1bP+.\{5\}##g
+# Mark cursor positioning codes \"Jr;c;
+s#${p}\([0-9]\{1,2\}\)G#\"J;\1;#g
+s#${p}\([0-9]\{1,2\}\);\([0-9]\{1,2\}\)H#\"J\1;\2;#g
+
+# Mark clear as \"Cn where n=1 is screen and n=0 is to end-of-line
+s#${p}H#\"C1;#g
+s#${p}K#\"C0;#g
+# Mark Cursor move columns as \"Mn where n is +ve for right, -ve for left
+s#${p}C#\"M1;#g
+s#${p}\([0-9]\{1,\}\)C#\"M\1;#g
+s#${p}\([0-9]\{1,\}\)D#\"M-\1;#g
+s#${p}\([0-9]\{1,\}\)P#\"X\1;#g
+
+s#${p}[0-9;?]*[^0-9;?m]##g
+
+" |
+
+# Normalize the input before transformation
+sed "
+# escape HTML (ampersand and quote done above)
+s#>#\>#g; s#<#\<#g;
+
+# normalize SGR codes a little
+
+# split 256 colors out and mark so that they're not
+# recognised by the following 'split combined' line
+:e
+s#${p}\([0-9;]\{1,\}\);\([34]8;5;[0-9]\{1,3\}\)m#${p}\1m${p}¬\2m#g; t e
+s#${p}\([34]8;5;[0-9]\{1,3\}\)m#${p}¬\1m#g;
+
+:c
+s#${p}\([0-9]\{1,\}\);\([0-9;]\{1,\}\)m#${p}\1m${p}\2m#g; t c   # split combined
+s#${p}0\([0-7]\)#${p}\1#g                                 #strip leading 0
+s#${p}1m\(\(${p}[4579]m\)*\)#\1${p}1m#g                   #bold last (with clr)
+s#${p}m#${p}0m#g                                          #add leading 0 to norm
+
+# undo any 256 color marking
+s#${p}¬\([34]8;5;[0-9]\{1,3\}\)m#${p}\1m#g;
+
+# map 16 color codes to color + bold
+s#${p}9\([0-7]\)m#${p}3\1m${p}1m#g;
+s#${p}10\([0-7]\)m#${p}4\1m${p}1m#g;
+
+# change 'reset' code to \"R
+s#${p}0m#\"R;#g
+" |
+
+# Convert SGR sequences to HTML
+sed "
+# common combinations to minimise html (optional)
+:f
+s#${p}3[0-7]m${p}3\([0-7]\)m#${p}3\1m#g; t f
+:b
+s#${p}4[0-7]m${p}4\([0-7]\)m#${p}4\1m#g; t b
+s#${p}3\([0-7]\)m${p}4\([0-7]\)m##g
+s#${p}4\([0-7]\)m${p}3\([0-7]\)m##g
+
+s#${p}1m##g
+s#${p}4m##g
+s#${p}5m##g
+s#${p}7m##g
+s#${p}9m##g
+s#${p}3\([0-9]\)m##g
+s#${p}4\([0-9]\)m##g
+
+s#${p}38;5;\([0-9]\{1,3\}\)m##g
+s#${p}48;5;\([0-9]\{1,3\}\)m##g
+
+s#${p}[0-9;]*m##g # strip unhandled codes
+" |
+
+# Convert alternative character set and handle cursor movement codes
+# Note we convert here, as if we do at start we have to worry about avoiding
+# conversion of SGR codes etc., whereas doing here we only have to
+# avoid conversions of stuff between &...; or <...>
+#
+# Note we could use sed to do this based around:
+#   sed 'y/abcdefghijklmnopqrstuvwxyz{}`~/▒␉␌␍␊°±␤␋┘┐┌└┼⎺⎻─⎼⎽├┤┴┬│≤≥π£◆·/'
+# However that would be very awkward as we need to only conv some input.
+# The basic scheme that we do in the awk script below is:
+#  1. enable transliterate once "T1; is seen
+#  2. disable once "T0; is seen (may be on diff line)
+#  3. never transliterate between &; or <> chars
+#  4. track x,y movements and active display mode at each position
+#  5. buffer line/screen and dump when required
+sed "
+# change 'smacs' and 'rmacs' to a single char so that we can easily do
+# negative matching, without using look-behind expressions etc.
+s#\x1b(0#\"T1;#g;
+s#\x0E#\"T1;#g;
+
+s#\x1b(B#\"T0;#g
+s#\x0F#\"T0;#g
+" |
+(
+gawk '
+function dump_line(l,del,c,blanks,ret) {
+  for(c=1;c")
+  for(i=1;i<=spc;i++) {
+    rm=rm?rm:(a[i]!=attr[i]">")
+    if(rm) {
+      ret=ret ""
+      delete a[i];
+    }
+  }
+  for(i=1;i"
+    if(a[i]!=attr[i]) {
+      a[i]=attr[i]
+      ret = ret attr[i]
+    }
+  }
+  return ret
+}
+
+function encode(string,start,end,i,ret,pos,sc,buf) {
+   if(!end) end=length(string);
+   if(!start) start=1;
+   state=3
+   for(i=1;i<=length(string);i++) {
+     c=substr(string,i,1)
+     if(state==2) {
+       sc=sc c
+       if(c==";") {
+          c=sc
+          state=last_mode
+       } else continue
+     } else {
+       if(c=="\r") { x=1; continue }
+       if(c=="<") {
+         # Change attributes - store current active
+         # attributes in span array
+         split(substr(string,i),cord,">");
+         i+=length(cord[1])
+         span[++spc]=cord[1] ">"
+         continue
+       }
+       else if(c=="&") {
+         # All goes to single position till we see a semicolon
+         sc=c
+         state=2
+         continue
+       }
+       else if(c=="\b") {
+          # backspace move insertion point back 1
+          if(spc) attr[x,y]=atos(span)
+          x=x>1?x-1:1
+          continue
+       }
+       else if(c=="\"") {
+          split(substr(string,i+2),cord,";")
+          cc=substr(string,i+1,1);
+          if(cc=="T") {
+              # Transliterate on/off
+              if(cord[1]==1&&state==3) last_mode=state=4
+              if(cord[1]==0&&state==4) last_mode=state=3
+          }
+          else if(cc=="C") {
+              # Clear
+              if(cord[1]+0) {
+                # Screen - if Recording dump screen
+                if(dumpStatus==dsActive) ret=ret dump_screen()
+                dumpStatus=dsActive
+                delete dump
+                delete attr
+                x=y=1
+              } else {
+                # To end of line
+                for(pos=x;posmaxY) maxY=y
+                # Change y - start recording
+                dumpStatus=dumpStatus?dumpStatus:dsReset
+              }
+          }
+          else if(cc=="M") {
+              # Move left/right on current line
+              x+=cord[1]
+          }
+          else if(cc=="X") {
+              # delete on right
+              for(pos=x;pos<=maxX;pos++) {
+                nx=pos+cord[1]
+                if(nx=start&&i<=end&&c in Trans) c=Trans[c]
+     }
+     if(dumpStatus==dsReset) {
+       delete dump
+       delete attr
+       ret=ret"\n"
+       dumpStatus=dsActive
+     }
+     if(dumpStatus==dsNew) {
+       # After moving/clearing we are now ready to write
+       # somthing to the screen so start recording now
+       ret=ret"\n"
+       dumpStatus=dsActive
+     }
+     if(dumpStatus==dsActive||dumpStatus==dsOff) {
+       dump[x,y] = c
+       if(!spc) delete attr[x,y]
+       else attr[x,y] = atos(span)
+       if(++x>maxX) maxX=x;
+     }
+    }
+    # End of line if dumping increment y and set x back to first col
+    x=1
+    if(!dumpStatus) return ret dump_line(y,1);
+    else if(++y>maxY) maxY=y;
+    return ret
+}
+BEGIN{
+  OFS=FS
+  # dump screen status
+  dsOff=0    # Not dumping screen contents just write output direct
+  dsNew=1    # Just after move/clear waiting for activity to start recording
+  dsReset=2  # Screen cleared build new empty buffer and record
+  dsActive=3 # Currently recording
+  F="abcdefghijklmnopqrstuvwxyz{}`~"
+  T="▒␉␌␍␊°±␤␋┘┐┌└┼⎺⎻─⎼⎽├┤┴┬│≤≥π£◆·"
+  maxX=80
+  delete cur;
+  x=y=1
+  for(i=1;i<=length(F);i++)Trans[substr(F,i,1)]=substr(T,i,1);
+}
+
+{ $0=encode($0) }
+1
+END {
+  if(dumpStatus) {
+    print dump_screen();
+  }
+}'
+)
+
+printf '
+ +\n' -- 1.8.5.3