tohtml.pre.sh

   1 #!/bin/sh
   2
   3 export LC_ALL=C
   4 sed 's/&/\&amp;/g;s/</\&lt;/g;s/>/\&gt;/g' | awk '
   5 BEGIN {
   6         getline
   7         print "<html><head><title>" $0 "</title></head><body><pre>"
   8         print
   9
  10         while (getline == 1) {
  11                 if ($0 ~ /^Contents/)
  12                         break
  13                 print
  14         }
  15         print "<a name=\"Contents\" href=\"#Contents\">Contents</a>"
  16
  17         while (getline == 1) {
  18                 id = $1
  19                 if (id ~ /Annex/)
  20                         id = $2
  21                 if (id ~ /^([1-9A-Z]|Index|Foreword|Introduction|Bibliography)/) {
  22                         if (match($0, /&lt;[a-zA-Z0-9_]*\.h&gt;/)) {
  23                                 h=substr($0,RSTART,RLENGTH)
  24                                 if (!(h in header))
  25                                         header[h] = id
  26                         }
  27                         if (id ~ /\.$/)
  28                                 id = substr(id,1,length(id)-1)
  29                         s = "<a href=\"#" id "\">" $0
  30                         if ($(NF-1) == ".")
  31                                 print s "</a>"
  32                         else{
  33                                 print s
  34                                 getline
  35                                 print $0 "</a>"
  36                         }
  37                         if (id == "Index")
  38                                 break
  39                 } else
  40                         print
  41         }
  42         note = 1
  43 }
  44
  45 !seenindex && /^ *([1-9A-Z]\.|Annex|Index|Foreword|Introduction|Bibliography)/ {
  46         id = $1
  47         if (id ~ /Annex/)
  48                 id = $2
  49         if (($0 ~ /^    [1-9]\./ || id ~ /^([A-Z]|[1-9A-Z]\.[1-9][0-9.]*|Index|Foreword|Introduction|Bibliography)$/) &&
  50             (NF==1 || $2 ~ /^[A-Zv]/) &&
  51             ($0 !~ /^ *[0-9.]+[^0-9]$/)) {
  52                 if (id ~ /\.$/)
  53                         id = substr(id,1,length(id)-1)
  54                 print "<a name=\"" id "\" href=\"#" id "\"><b>" $0 "</b></a>"
  55                 if (id == "Index")
  56                         seenindex=1
  57                 next
  58         }
  59 }
  60
  61 /^\[page / {
  62         p = substr($2,1,length($2)-1)
  63         print "[<a name=\"p" p "\" href=\"#p" p "\">page " p "</a>] (<a href=\"#Contents\">Contents</a>)"
  64         next
  65 }
  66
  67 /^ *(Syntax|Semantics|Description|Constraints|Synopsis|Returns)$/ {
  68         print "<b>" $0 "</b>"
  69         next
  70 }
  71
  72 {
  73         s = $0
  74         p = ""
  75         if (seenindex)
  76                 r = "[ (][A-Z1-9][0-9.]*"
  77         else
  78                 r = "[ (][A-Z1-9]\\.[0-9.]*[0-9]"
  79         while (match(s, r)) {
  80                 p = p substr(s,1,RSTART)
  81                 m = substr(s,RSTART+1,RLENGTH-1)
  82                 if (m ~ /\.0$/ || m ~ /[4-9][0-9]/ || m ~ /[0-3][0-9][0-9]/ || substr(s,RSTART+RLENGTH,1) ~ /[a-zA-Z\-]/)
  83                         p = p m
  84                 else
  85                         p = p "<a href=\"#" m "\">" m "</a>"
  86                 s = substr(s,RSTART+RLENGTH)
  87         }
  88         s = p s
  89         p = ""
  90         while (match(s, /[Aa]nnex [A-Z]/)) {
  91                 p = p substr(s,1,RSTART-1)
  92                 m = substr(s,RSTART,RLENGTH)
  93                 p = p "<a href=\"#" substr(m,RLENGTH,1) "\">" m "</a>"
  94                 s = substr(s,RSTART+RLENGTH)
  95         }
  96         s = p s
  97         p = ""
  98         while (match(s, /&lt;[a-zA-Z0-9_]*\.h&gt;/)) {
  99                 p = p substr(s,1,RSTART-1)
 100                 m = substr(s,RSTART,RLENGTH)
 101                 if (m in header)
 102                         p = p "<a href=\"#" header[m] "\">" m "</a>"
 103                 else
 104                         p = p m
 105                 s = substr(s,RSTART+RLENGTH)
 106         }
 107         s = p s
 108         p = ""
 109         while (match(s, note "\\)")) {
 110                 if (note==1 && s !~ /\.1\)/)
 111                         break
 112                 p = p substr(s,1,RSTART-1)
 113                 p = p "<sup><a href=\"#note" note "\"><b>" note ")</b></a></sup>"
 114                 note++
 115                 s = substr(s,RSTART+RLENGTH)
 116         }
 117         s = p s
 118         if (s ~ /^ *[1-9][0-9]*\) /) {
 119                 sub(/\)/,"",s)
 120                 sub(/[0-9]+/,"<sup><a name=\"note&\" href=\"#note&\"><b>&)</b></a></sup>",s)
 121         }
 122         print s
 123 }
 124
 125 END { print "</pre></body></html>" }'