国标GB/T4754的HTML转换程序
戻る
- GB/T4754-2002(国民经济行业分类)是一张大表,原文是Word文件,转换成HTML文件有3509KB。
决定编程序(利用HTML::Template)转换成轻便的HTML文件。
- 把Word的文件抓到Excel文件,然后用Unicode TXT保存(注意必须用Unicode保存)。
- Template是gbt4754_0.htm,见下面。
- Perl程序是gbt4754.pl,见下面。
- 最终成果=>gbt4754_2002.htm,263KB,是Word变换的HMLT文件十三分之一。
- 注意点1:EXCEL的Unicode是UTF-16LE,变换HTML文件之前,TXT文本文件要转换成UTF8格式。
- 注意点2:如果程序中使用分割符号(此处是XX),程序本身也必须用UTF8保存。
这儿采用的办法是把分割符号放在name.txt文件中。
- 程序进行了大幅修改,见下面。把HTML的＜td＞等也作为变量来考虑!
gbt4754_2002.htm变成了221KB。
- 对该程序稍作改动(见最下面的safe.pl),生成新的表格==>安全生产专用设备企业所得税优惠目录(2008年版)
- 3835.pl==>第一批信息安全产品强制性认证目录
gbt4754_0.htm(new)
<![CDATA[
<HTML>
<HEAD>
<META http-equiv="Content-Type" content="text/html; charset=UTF-8">
<TITLE>GB/T4754-2002,国民经济行业分类,Industrial classification for national economic activities</TITLE>
</HEAD>
<BODY bgcolor="#FFFFFF">
<center>
<h2>GB/T4754-2002,国民经济行业分类,Industrial classification for national economic activities</h2>
</center>
<a href="economic1.htm">返回</a>
<hr color="#003366">
<center>
<table width=85% align="center" border=1 cellpadding=5>
<tr bgcolor="#3399FF" align="center">
<th colspan=4 width=20%>代码</th>
<th rowspan=2 width=40%>类别名称</th>
<th rowspan=2 width=40%>说明</th>
</tr>
<tr bgcolor="#3399FF" align="center">
<th>门类</th>
<th>大类</th>
<th>中类</th>
<th>小类</th>
</tr>
<TMPL_LOOP NAME="LOOP">
<tr bgcolor="lightcyan">
<TMPL_VAR NAME="LINE1">
</tr>
</TMPL_LOOP>
<tr bgcolor="#3399FF" align="center">
<th>门类</th>
<th>大类</th>
<th>中类</th>
<th>小类</th>
<th rowspan=2 width=40%>类别名称</th>
<th rowspan=2 width=40%>说明</th>
</tr>
<tr bgcolor="#3399FF" align="center">
<th colspan=4 width=20%>代码</th>
</tr>
</table>
<br><br>
<h3>企业登记注册类型（国统[1998]200号）</h3>
<table width=85% align="center" border=1 cellpadding=5>
<tr bgcolor="#3399FF" align="center">
<th width=20%>编码</th>
<th width=80%>企业登记注册类型</th>
</tr>
<TMPL_LOOP NAME="LOOP2">
<tr bgcolor="lightcyan" align="left">
<td><TMPL_VAR NAME="A"></td>
<td><TMPL_VAR NAME="B"></td>
</tr>
</TMPL_LOOP>
</table>
<hr color="#003366">
</center>
<a href="economic1.htm">返回</a><br>
</BODY>
</HTML>
]]>
-------------------------------------------
gbt4754_0.htm(old)
<![CDATA[
<HTML>
<HEAD>
<META http-equiv="Content-Type" content="text/html; charset=UTF-8">
<TITLE>GB/T4754-2002,国民经济行业分类,Industrial classification for national economic activities</TITLE>
</HEAD>
<BODY bgcolor="#FFFFFF">
<center>
<h2>GB/T4754-2002,国民经济行业分类,Industrial classification for national economic activities</h2>
</center>
<a href="economic1.htm">返回</a>
<hr color="#003366">
<center>
<table width=85% align="center" border=1 cellpadding=5>
<tr bgcolor="#3399FF" align="center">
<th colspan=4 width=20%>代码</th>
<th rowspan=2 width=40%>类别名称</th>
<th rowspan=2 width=40%>说明</th>
</tr>
<tr bgcolor="#3399FF" align="center">
<th>门类</th>
<th>大类</th>
<th>中类</th>
<th>小类</th>
</tr>
<TMPL_LOOP NAME="LOOP">
<tr bgcolor="lightcyan" align="left">
<td><TMPL_VAR NAME="A1"></td>
<td><TMPL_VAR NAME="A2"></td>
<td><TMPL_VAR NAME="A3"></td>
<td><TMPL_VAR NAME="A4"></td>
<td><TMPL_VAR NAME="B1"></td>
<td><TMPL_VAR NAME="C1"></td>
</tr>
</TMPL_LOOP>
<tr bgcolor="#3399FF" align="center">
<th>门类</th>
<th>大类</th>
<th>中类</th>
<th>小类</th>
<th rowspan=2 width=40%>类别名称</th>
<th rowspan=2 width=40%>说明</th>
</tr>
<tr bgcolor="#3399FF" align="center">
<th colspan=4 width=20%>代码</th>
</tr>
</table>
<h3>企业登记注册类型（国统[1998]200号）</h3>
<table width=85% align="center" border=1 cellpadding=5>
<tr bgcolor="#3399FF" align="center">
<th width=20%>编码</th>
<th width=80%>企业登记注册类型</th>
</tr>
<TMPL_LOOP NAME="LOOP2">
<tr bgcolor="lightcyan" align="left">
<td><TMPL_VAR NAME="A"></td>
<td><TMPL_VAR NAME="B"></td>
</tr>
</TMPL_LOOP>
</table>
<hr color="#003366">
</center>
<a href="economic1.htm">返回</a><br>
</BODY>
</HTML>
]]>
-------------------------------------------
gbt4754_0.pl(new)
<![CDATA[
# gbt4754.pl
use strict;
use HTML::Template;
use utf8;
my(%t,@fld,$n,$template,@loop,@loop2);
open(IN,"name.txt") or die "Can't open the file name.txt.\n";
while(<IN>) {
if ( /^8888/ ) {
@fld = split;
$t{d1} = $fld[1];
}
}
close(IN);
# Read csv data
@loop = ();
$t{NO} = 0;
open(IN,"gbt4754.txt") or die "Can't open the file gbt4754.txt.\n";
while(<IN>){
next if $. == 1;
chop;
$t{NO}++;
$t{TYPE1} = 0;
@fld = split($t{d1});
$t{A1} = $fld[0];
if ( $t{A1} =~ /[A-Z]/ ) {
$t{A1} =~ s/\s$//g; # 把末尾的空格去掉
$t{LINE_A1}{$t{NO}} = $t{A1};
$t{TYPE1} = 'A1';
$t{A1_old} = $t{A1};
$t{lists}{$t{A2_old}}--; # A1类侵占了A2类的位置,需要减去1
$t{lists}{$t{A3_old}}--; # A1类侵占了A3类的位置,需要减去1
} else {
$t{lists}{$t{A1_old}}++; # A1类自己增加一个空格
}
$t{A2} = $fld[1] + 0;
if ( $t{A2} != 0 ) {
$t{A2} = sprintf("%02d",$t{A2});
$t{LINE_A2}{$t{NO}} = $t{A2};
$t{TYPE1} = 'A2';
$t{A2_old} = $t{A2};
$t{lists}{$t{A3_old}}--; # A2类侵占了A3类的位置,需要减去1
} else {
$t{lists}{$t{A2_old}}++; # A2类自己增加一个空格
}
$t{A3} = $fld[2] + 0;
if ( $t{A3} != 0 ) {
$t{A3} = sprintf("%03d",$t{A3});
$t{LINE_A3}{$t{NO}} = $t{A3};
$t{TYPE1} = 'A3';
$t{A3_old} = $t{A3};
} else {
$t{lists}{$t{A3_old}}++;
}
$t{A4} = $fld[3] + 0;
if ( $t{A4} != 0 ) {
$t{A4} = sprintf("%04d",$fld[3]);
}
$t{LINE_A4}{$t{NO}} = $t{A4};
$t{LINE_B1}{$t{NO}} = $fld[4];
$t{LINE_C1}{$t{NO}} = $fld[5];
if ( $t{TYPE1} ) {
push(@{ $t{LINE_TYPE} },$t{TYPE1});
} else {
push(@{ $t{LINE_TYPE} },'A0');
}
}
close(IN);
# 把数据输出到HTML文件
for $n ( 1 .. $t{NO} ) {
$t{TYPE1} = $t{LINE_TYPE}[$n-1];
if ( $t{TYPE1} eq 'A1' ) {
$t{A1} = $t{LINE_A1}{$n};
$t{A1no} = $t{lists}{$t{A1}} + 1;
# 这个操作是关键! 出了变量$t{LINE_B1}{$n},其他的参数如 td,rowspan等也可以作为Template的变量!
$t{LINE1} = '<td valign="top" rowspan=' . $t{A1no} . '>';
$t{LINE1} .= $t{A1} . '</td>';
$t{LINE1} .= '<td colspan=3></td>';
$t{LINE1} .= '<td>' . $t{LINE_B1}{$n} . '</td>';
$t{LINE1} .= '<td>' . $t{LINE_C1}{$n} . '</td>';
} elsif ( $t{TYPE1} eq 'A2' ) {
$t{A2} = $t{LINE_A2}{$n};
$t{A2no} = $t{lists}{$t{A2}} + 1;
$t{LINE1} = '<td valign="top" rowspan=' . $t{A2no} . '>';
$t{LINE1} .= $t{A2} . '</td>';
$t{LINE1} .= '<td colspan=2></td>';
$t{LINE1} .= '<td>' . $t{LINE_B1}{$n} . '</td>';
$t{LINE1} .= '<td>' . $t{LINE_C1}{$n} . '</td>';
} elsif ( $t{TYPE1} eq 'A3' ) {
if ( $t{LINE_A4}{$n} == 0 ) {
$t{A3} = $t{LINE_A3}{$n};
$t{A3no} = $t{lists}{$t{A3}} + 1;
$t{LINE1} = '<td valign="top" rowspan=' . $t{A3no} . '>';
$t{LINE1} .= $t{A3} . '</td>';
$t{LINE1} .= '<td></td>';
$t{LINE1} .= '<td>' . $t{LINE_B1}{$n} . '</td>';
$t{LINE1} .= '<td>' . $t{LINE_C1}{$n} . '</td>';
} else {
$t{A3} = $t{LINE_A3}{$n};
$t{A3no} = $t{lists}{$t{A3}} + 1;
$t{LINE1} = '<td valign="top" rowspan=' . $t{A3no} . '>';
$t{LINE1} .= $t{A3} . '</td>';
$t{LINE1} .= '<td>' . $t{LINE_A4}{$n} . '</td>';
$t{LINE1} .= '<td>' . $t{LINE_B1}{$n} . '</td>';
$t{LINE1} .= '<td>' . $t{LINE_C1}{$n} . '</td>';
}
} else {
$t{LINE1} = '<td>' . $t{LINE_A4}{$n} . '</td>';
$t{LINE1} .= '<td>' . $t{LINE_B1}{$n} . '</td>';
$t{LINE1} .= '<td>' . $t{LINE_C1}{$n} . '</td>';
}
my %row = (
LINE1 => $t{LINE1}
);
push(@loop, \%row);
}
# 输出第二个表格
@loop2 = ();
open(IN,"gbt4754_2.txt") or die "Can't open the file gbt4754_2.txt.\n";
while(<IN>){
next if $. == 1;
chop;
@fld = split($t{d1});
$t{A} = $fld[0];
$t{B} = $fld[1];
if ( $#fld == 1 ) {
my %row = (
A => $t{A},
B => $t{B}
);
push(@loop2, \%row);
}
}
close(IN);
$template = HTML::Template->new(filename => "gbt4754_0.htm");
$template->param(loop => \@loop);
$template->param(loop2 => \@loop2);
open(OUT,">gbt4754_2002.htm");
print OUT $template->output;
close(OUT);
print "The output file is gbt4754_2002.htm\n";
__END__;
]]>
-------------------------------------------
gbt4754.pl(old)
<![CDATA[
# gbt4754.pl
use strict;
use HTML::Template;
use utf8;
my(%t,@fld,$n,$template,@loop,@loop2);
open(IN,"name.txt") or die "Can't open the file name.txt.\n";
while(<IN>) {
if ( /^8888/ ) {
@fld = split;
$t{d1} = $fld[1];
}
}
close(IN);
# Read csv data
@loop = ();
open(IN,"gbt4754.txt") or die "Can't open the file gbt4754.txt.\n";
while(<IN>){
next if $. == 1;
chop;
@fld = split($t{d1});
$t{A1} = $fld[0];
$t{A2} = $fld[1] + 0;
if ( $t{A2} != 0 ) {
$t{A2} = sprintf("%02d",$t{A2});
} else {
$t{A2} = '';
}
$t{A3} = $fld[2] + 0;
if ( $t{A3} != 0 ) {
$t{A3} = sprintf("%03d",$t{A3});
} else {
$t{A3} = '';
}
$t{A4} = $fld[3] + 0;
if ( $t{A4} != 0 ) {
$t{A4} = sprintf("%04d",$t{A4});
} else {
$t{A4} = '';
}
$t{B1} = $fld[4];
$t{C1} = $fld[5];
my %row = (
A1 => $t{A1},
A2 => $t{A2},
A3 => $t{A3},
A4 => $t{A4},
B1 => $t{B1},
C1 => $t{C1}
);
push(@loop, \%row);
}
close(IN);
@loop2 = ();
open(IN,"gbt4754_2.txt") or die "Can't open the file gbt4754_2.txt.\n";
while(<IN>){
next if $. == 1;
chop;
@fld = split($t{d1});
$t{A} = $fld[0];
$t{B} = $fld[1];
if ( $#fld == 1 ) {
my %row = (
A => $t{A},
B => $t{B}
);
push(@loop2, \%row);
}
}
close(IN);
$template = HTML::Template->new(filename => "gbt4754_0.htm");
$template->param(loop => \@loop);
$template->param(loop2 => \@loop2);
open(OUT,">gbt4754.htm");
print OUT $template->output;
close(OUT);
print "The output file is gbt4754.htm\n";
__END__;
]]>
-------------------------------------------
<![CDATA[
filename=name.txt
8888 XX
]]>
-------------------------------------------
EXCEL->TXT->HTML程序,safe.pl
<![CDATA[
use strict;
use HTML::Template;
use utf8;
my(%t,@fld,$n,$n1,$template,@loop);
open(IN,"name.txt") or die "Can't open the file name.txt.\n";
while(<IN>) {
if ( /^8888/ ) {
@fld = split;
$t{d1} = $fld[1];
$t{d2} = $fld[2];
$t{d3} = $fld[3];
}
}
close(IN);
# Read csv data
@loop = ();
$t{NO} = 0;
$t{NO1} = 0;
open(IN,"safe.txt") or die "Can't open the file safe.txt.\n";
while(<IN>){
chop;
$t{NO}++;
$t{TYPE1} = 0;
@fld = split($t{d1});
$t{A1} = $fld[0];
if ( $t{A1} =~ /$t{d2}/ ) {
$t{LINE_A1}{$t{NO}} = $t{A1};
$t{TYPE1} = 'A1';
$t{A1_old} = $t{A1};
} elsif ( $t{A1} =~ /$t{d3}/ ) {
$t{LINE_A1}{$t{NO}} = $t{NO1};
$t{TYPE1} = 'A2';
} else {
$t{lists}{$t{A1_old}}++;
}
if ( $t{TYPE1} eq 'A1') {
push(@{ $t{LINE_TYPE} },$t{TYPE1});
push(@{ $t{LINE_NO1} },$t{NO1});
} elsif ( $t{TYPE1} eq 'A2' ) {
push(@{ $t{LINE_TYPE} },$t{TYPE1});
push(@{ $t{LINE_NO1} },$t{NO1});
@{ $t{LINE_B}{$t{NO}} } = @fld;
} else {
$t{NO1}++;
push(@{ $t{LINE_TYPE} },'A0');
push(@{ $t{LINE_NO1} },$t{NO1});
@{ $t{LINE_B}{$t{NO}} } = @fld;
}
}
close(IN);
for $n ( 1 .. $t{NO} ) {
$t{TYPE1} = $t{LINE_TYPE}[$n-1];
$t{NO1} = $t{LINE_NO1}[$n-1];
if ( $t{TYPE1} eq 'A1' ) {
$t{A1} = $t{LINE_A1}{$n};
$t{A1no} = $t{lists}{$t{A1}} + 1;
$t{LINE1} = '<td colspan=6>';
$t{LINE1} .= $t{A1} . '</td>';
} elsif ( $t{TYPE1} eq 'A2' ) {
$t{A1} = $t{LINE_A1}{$n};
$t{LINE1} = '<td>';
$t{LINE1} .= $t{A1} . '</td>';
@fld = @{ $t{LINE_B}{$n} };
for $n1 ( 1 .. $#fld ) {
$t{LINE1} .= '<td>' . $fld[$n1] . '</td>';
}
} else {
$t{NO1} = sprintf("%02d",$t{NO1});
$t{LINE1} = '<td>' . $t{NO1} . '</td>';
@fld = @{ $t{LINE_B}{$n} };
for $n1 ( 1 .. $#fld ) {
$t{LINE1} .= '<td>' . $fld[$n1] . '</td>';
}
}
my %row = (
LINE1 => $t{LINE1}
);
push(@loop, \%row);
}
$template = HTML::Template->new(filename => "safe0.htm");
$template->param(loop => \@loop);
open(OUT,">safe_2008.htm");
print OUT $template->output;
close(OUT);
]]>
EXCEL->TXT->HTML程序,3835.pl
<![CDATA[
use strict;
use HTML::Template;
use utf8;
my(%t,@fld,$n,$template,@loop);
#print "Please input filename(*.txt)=";
#chop($t{root}=<STDIN>);
$t{inputf} = '3835.txt';
$t{htm0} = 'it0.htm';
$t{outputf} = 'it1.htm';
open(IN,"name.txt") or die "Can't open the file name.txt.\n";
while(<IN>) {
if ( /^8888/ ) {
@fld = split;
$t{d1} = $fld[1];
}
}
close(IN);
# Read excel data
@loop = ();
$t{NO} = 0;
open(IN,"$t{inputf}") or die "Can't open the file $t{inputf}.\n";
while(<IN>){
chop;
$t{NO}++;
@fld = split($t{d1});
$t{LINE_C1}{$t{NO}} = $fld[2];
if ( $t{NO} % 2 == 1 ) {
$t{LINE_B1}{$t{NO}} = $fld[1];
} else {
$t{LINE_B1}{$t{NO}} = 0;
}
$t{TYPE1} = 0;
$t{A1} = $fld[0];
if ( $t{A1} ne "\t" ) {
$t{TYPE1} = 'A1';
$t{LINE_A1}{$t{NO}} = $fld[0];
$t{P1} = 'P' . $t{NO};
$t{lists}{$t{P1}}++;
} else {
$t{lists}{$t{P1}}++;
}
if ( $t{TYPE1} && $t{LINE_B1}{$t{NO}} ) {
$t{LINE_TYPE}{$t{NO}} = 'A1';
} elsif ( $t{TYPE1} == 0 && $t{LINE_B1}{$t{NO}} ) {
$t{LINE_TYPE}{$t{NO}} = 'A2';
} else {
$t{LINE_TYPE}{$t{NO}} = 'A0';
}
}
close(IN);
for $n ( 1 .. $t{NO} ) {
$t{TYPE1} = $t{LINE_TYPE}{$n};
if ( $t{TYPE1} eq 'A1' ) {
$t{A1} = $t{LINE_A1}{$n};
$t{P1} = 'P' . $n;
$t{P1no} = $t{lists}{$t{P1}};
$t{LINE1} = '<tr bgcolor="lightcyan"><td rowspan=' . $t{P1no} . '>';
$t{LINE1} .= $t{A1} . '</td>';
$t{LINE1} .= '<td rowspan=2>' . $t{LINE_B1}{$n} . '</td>';
$t{LINE1} .= '<td>' . $t{LINE_C1}{$n} . '</td></tr>';
} elsif ( $t{TYPE1} eq 'A2' ) {
$t{LINE1} = '<tr bgcolor="lightcyan">';
$t{LINE1} .= '<td rowspan=2>' . $t{LINE_B1}{$n} . '</td>';
$t{LINE1} .= '<td>' . $t{LINE_C1}{$n} . '</td></tr>';
} elsif ( $t{TYPE1} eq 'A0' ) {
$t{LINE1} = '<tr bgcolor="lightcyan">';
$t{LINE1} .= '<td>' . $t{LINE_C1}{$n} . '</td></tr>';
} else {
print "ERROR!\n";
exit;
}
my %row = (
LINE1 => $t{LINE1}
);
push(@loop, \%row);
}
$template = HTML::Template->new(filename => "$t{htm0}");
$template->param(loop => \@loop);
open(OUT,">$t{outputf}");
print OUT $template->output;
close(OUT);
]]>
戻る