能这是否可以推广使用某种正则表达式,而不仅仅是索引,然后使用一些可修改的任意分隔符(例如空格)提取和评估所选行开头或结尾的数字?谢谢
% 样本输出:
\ReadFile{\myarray}{somefile.txt}
\myarray{text:}{end}[]
11
\myarray{3}{end}[]
11
\myarray{text:}{beginning}[]
NA
\myarray{13}{beginning}[]
NA
\myarray{_top_}{end}[]
NA
\myarray{_top_}{beginning}[]
46 %45+1+0
\myarray{new stuff}{end}[]
NA
\myarray{three}{beginning}[]
93 %90+3+0
% 示例乳胶代码file.tex
\documentclass{article}
\usepackage{xparse}
\ExplSyntaxOn
\ior_new:N \g_hringriin_file_stream
\NewDocumentCommand{\ReadFile}{mm}
{
\hringriin_read_file:nn { #1 } { #2 }
\cs_new:Npn #1 ##1
{
\str_if_eq:nnTF { ##1 } { * }
{ \seq_count:c { g_hringriin_file_ \cs_to_str:N #1 _seq } }
{ \seq_item:cn { g_hringriin_file_ \cs_to_str:N #1 _seq } { ##1 } }
}
}
\cs_new_protected:Nn \hringriin_read_file:nn
{
\ior_open:Nn \g_hringriin_file_stream { #2 }
\seq_gclear_new:c { g_hringriin_file_ \cs_to_str:N #1 _seq }
\ior_map_inline:Nn \g_hringriin_file_stream
{
\seq_gput_right:cx
{ g_hringriin_file_ \cs_to_str:N #1 _seq }
{ \tl_trim_spaces:n { ##1 } }
}
\ior_close:N \g_hringriin_file_stream
}
% 样本数据somearray.txt
File: file.tex
Encoding: ascii
Words in text: 11
Words in headers: 12
Words outside text (captions, etc.): 13
Number of headers: 31
Number of floats/tables/figures: 32
Number of math inlines: 33
Number of math displayed: 34
Subcounts:
text+headers+captions (#headers/#floats/#inlines/#displayed)
45+1+0 (1/0/0/0) _top_
56+1+0 (1/0/1/0) Section: Beginning
67+2+0 (1/0/0/0) Section: Main part
78+5+0 (1/0/1/1) Subsection: Sub part one new stuff
894+5+0 (1/0/2/0) Subsection: Sub part two old stuff
90+3+0 (1/0/0/0) Subsection: Sub part three
12+1+0 (1/0/0/0) Section: End
答案1
这里不需要正则表达式,您可以使用自定义分隔的宏参数来分离行,并使用自定义宏来访问值。
\documentclass{article}
\newread\fl
\openin\fl=somearray.txt
\def\splitlineA#1:#2\relax{%
\def\lastline{#1}%
\ifx\lastline\Subcountstest
\let\splitline\splitlineB
\else
\expandafter\gdef\csname FL-#1\endcsname{#2}%
\fi
}
\def\splitlineB#1+#2+#3 (#4/#5/#6/#7)#8\relax{%
\expandafter\gdef\csname FL-#8\endcsname{{#1}{#2}{#3}{#4}{#5}{#6}{#7}}%
}
\def\Subcountstest{Subcounts}
{
\catcode`\#=12
\let\splitline\splitlineA
\makeatletter
\endlinechar=-1
\loop
\read\fl to \tmp
\ifx\@empty\tmp
\else
\expandafter\splitline\tmp\relax
\repeat
}
\def\FLval#1{\csname FL-#1\endcsname}
\def\FLsubcount#1#2{%
\def\tmp##1##2##3##4##5##6##7{###2}%
\expandafter\expandafter\expandafter\tmp\csname FL- #1\endcsname}
\begin{document}
\textbf{Words in headers} = \FLval{Words in headers}
\textbf{Number of headers} = \FLval{Number of headers}
\textbf{text} in \textbf{Subsection: Sub part three} = \FLsubcount{Subsection: Sub part three}{1}
\textbf{inlines} in \textbf{Subsection: Sub part two old stuff} = \FLsubcount{Subsection: Sub part two old stuff}{6}
\end{document}
评论中请求的版本将 #1+#2+#3 相加并丢弃接下来的 4 个数字
\documentclass{article}
\makeatletter
\newread\fl
\openin\fl=somearray.txt
\def\splitlineA#1:#2\relax{%
\def\lastline{#1}%
\ifx\lastline\Subcountstest
\let\splitline\splitlineB
\else
\expandafter\gdef\csname FL-#1\endcsname{#2}%
\fi
}
\def\splitlineB#1+#2+#3 (#4/#5/#6/#7)#8\relax{%
\def\tmpa{#1}\ifx\tmpa\texttest\else
\expandafter\xdef\csname FL-\@firstofone#8\endcsname{\the\numexpr#1+#2+#3}%
\fi
}
\def\texttest{text}
\def\Subcountstest{Subcounts}
{
\catcode`\#=12
\let\splitline\splitlineA
\endlinechar=-1
\loop
\read\fl to \tmp
\ifx\@empty\tmp
\else
\expandafter\splitline\tmp\relax
\repeat
}
\makeatother
\def\FLval#1{\csname FL-#1\endcsname}
\begin{document}
\textbf{Words in headers} = \FLval{Words in headers}
\textbf{Number of headers} = \FLval{Number of headers}
\textbf{Subsection: Sub part three} = \FLval{Subsection: Sub part three}
\textbf{Subsection: Sub part two old stuff} = \FLval{Subsection: Sub part two old stuff}
\end{document}