docb_html_util.erl

来自「OTP是开放电信平台的简称」· ERL 代码 · 共 537 行 · 第 1/2 页

%% ``The contents of this file are subject to the Erlang Public License,
%% Version 1.1, (the "License"); you may not use this file except in
%% compliance with the License. You should have received a copy of the
%% Erlang Public License along with this software. If not, it can be
%% retrieved via the world wide web at http://www.erlang.org/.
%% 
%% Software distributed under the License is distributed on an "AS IS"
%% basis, WITHOUT WARRANTY OF ANY KIND, either expressed or implied. See
%% the License for the specific language governing rights and limitations
%% under the License.
%% 
%% The Initial Developer of the Original Code is Ericsson Utvecklings AB.
%% Portions created by Ericsson are Copyright 1999-2000, Ericsson 
%% Utvecklings AB. All Rights Reserved.''
%% 
%%     $Id$
%%
-module(docb_html_util).

-export([attribute_cdata_to_html/1,
	 element_cdata_to_html/1,
	 pcdata_to_html/1, pcdata_to_html/2]).
-export([copy_pics/3]).
-export([extract_header_data/2, all_header_data/1]).
-export([make_uri/1,
	 make_anchor_href/1, make_anchor_href_short/3,
	 make_anchor_name_short/2,
	 make_funcdef_short/2]).
-export([erl_include/2, code_include/2, erl_eval/1]).
-export([number/3, count_sections/1]).
-export([format_toc/1]).
-export([html_latin1_sort_order/1]).

%%--Handle CDATA and PCDATA---------------------------------------------

%% NB: Functions for transforming sgmls/XMerL data output to html.
%%     Do not use these for included text files (cf code_include and
%%     erl_include).

attribute_cdata_to_html(Data) ->
    data2html(Data, false).

element_cdata_to_html(Data) ->
    data2html(Data, false).

pcdata_to_html(Data) ->
    data2html(Data, true).

pcdata_to_html(Data, RmSp) ->
    data2html(Data, RmSp).

%% PCDATA, CDATA: Replace entities, and optionally delete
%% leading and multiple spaces. CDATA never contains entities to
%% replace.

%% data2html(Cs, RmSpace)
data2html([$>| Cs], RmSp) ->
    [$&, $#, $6, $2, $;| data2html(Cs, RmSp)];
data2html([$<| Cs], RmSp) ->
    [$&, $#, $6, $0, $;| data2html(Cs, RmSp)];
data2html([$&| Cs], RmSp) ->
    [$&, $#, $3, $8, $;| data2html(Cs, RmSp)];
data2html([$\"| Cs], RmSp) ->
    [$&, $#, $3, $4, $;| data2html(Cs, RmSp)];
data2html([$\n| Cs], RmSp) ->
    data2html(Cs, RmSp);
data2html([$\\, $n| Cs], false) ->
    [$\n| data2html(Cs, false)];
data2html([$\\, $n| Cs], true) ->
    [$\n| data2html(delete_leading_space(Cs), true)];
data2html([$ , $ | Cs], true) ->		% delete multiple space
    [$ | data2html(delete_leading_space(Cs), true)];
data2html([$\\, $|| Cs0], RmSp) ->
    {Ent, Cs1} = collect_entity(Cs0),
    [entity_to_html(Ent)|  data2html(Cs1, RmSp)];
data2html([$\\, $0, $1, $2| Cs], RmSp) ->
    data2html(Cs, RmSp);
data2html([$\\, $\\, $n| Cs], RmSp) ->
    [$\\, $n| data2html(Cs, RmSp)];
data2html([$\\, O1, O2, O3| Cs], RmSp)
  when O1 >= $0, O1 =< $7, O2 >= $0, O2 =< $7, O3 >= $0, O3 =< $7 ->
    case octal2dec(O1, O2, O3) of
	173 ->					% soft hyphen
	    data2html(Cs, RmSp);
	C when C > 31, C < 256 ->
	    Ent = io_lib:format("&#~w;", [C]),
	    [Ent|  data2html(Cs, RmSp)];
	C ->
	    [C| data2html(Cs, RmSp)]
    end;
data2html([$\\, $\\| Cs], RmSp) ->
    [$\\| data2html(Cs, RmSp)];
data2html([C| Cs], RmSp) ->
    [C| data2html(Cs, RmSp)];
data2html([], _) ->
    [].

delete_leading_space([$ | Cs]) ->
    delete_leading_space(Cs);
delete_leading_space(Cs) ->
    Cs.

collect_entity(Data) ->
    collect_entity(Data, []).

collect_entity([$\\, $|| Cs], Rs) ->
    {lists:reverse(Rs), Cs};
collect_entity([C| Cs], Rs) ->
    collect_entity(Cs, [C| Rs]);
collect_entity([], Rs) ->
    {[], lists:reverse(Rs)}.

entity_to_html("&") -> "&#38;";
entity_to_html("\"") -> "&#34;";
entity_to_html("<") -> "&#60;";
entity_to_html(">") -> "&#62;";
entity_to_html([$\\, O1, O2, O3])
  when O1 >= $0, O1 =< $7, O2 >= $0, O2 =< $7, O3 >= $0, O3 =< $7 ->
    case octal2dec(O1, O2, O3) of
	173 ->					% soft hyphen
	    "";
	Value ->
	    io_lib:format("&#~w;", [Value])
    end;
entity_to_html(Other) ->
    docb_html_util_iso:entity_to_html(Other).

octal2dec(O1, O2, O3) ->
    (O1*8+O2)*8+O3-73*$0.

%%--Copy images---------------------------------------------------------

copy_pics(Src, Dest, Opts) ->
    Dir = code:lib_dir(docbuilder),
    InFile = filename:join([Dir, "etc", Src]),
    OutFile = docb_util:outfile(Dest, "", Opts),

    case filelib:last_modified(OutFile) of
	0 -> % File doesn't exist
	    file:copy(InFile, OutFile);

	OutMod2 ->
	    InMod1s = calendar:datetime_to_gregorian_seconds(
			filelib:last_modified(InFile)),
	    OutMod2s = calendar:datetime_to_gregorian_seconds(OutMod2),
	    if
		InMod1s > OutMod2s -> % InFile is newer than OutFile
		    file:copy(InFile, OutFile);
		true ->
		    ok
	    end
    end.

%%--Resolve header data-------------------------------------------------

extract_header_data(Key, {header, [], List}) ->
    case lists:keysearch(Key, 1, List) of
	{value, {Key, [], []}} ->
	    "";
	{value, {Key, [], [{pcdata, [], Value}]}} ->
	    pcdata_to_html(Value);
	false ->
	    ""
    end.

all_header_data(Header) ->
    all_header_data(Header,
		    [title, prepared, responsible, docno, approved,
		     checked, date, rev, file]).

all_header_data(_Header, []) ->
    [];
all_header_data(Header, [Key| Rest]) ->
    [extract_header_data(Key, Header) | all_header_data(Header, Rest)].

%%--Resolve hypertext references----------------------------------------

%% URI regular expression (RFC 2396):
%%    "^(([^:/?#]+):)?(//([^/?#]*))?([^?#]*)(\\?([^#]*))?(#(.*))?"
%% We split it in five parts:
%% scheme:	"^(([^:/?#]+):)?"	(includes trailing `:')
%% authority:	"^(//([^/?#]*))?"	(includes leading `//')
%% path:	"^([^?#]*)"
%% query:	"^(\\?([^#]*))?"	(includes leading `?')
%% fragment:	"^(#(.*))?"		(includes leading `#')

make_uri(Cs) ->
    lists:flatmap(
      fun({path, S}) ->
	      case regexp:match(S, "\.xml?\$") of
		  {match, _, _} ->
		      {ok, NS, _} = regexp:sub(S, "\.xml?\$", ".html"),
		      NS;
		  _  ->
		      S
	      end;
	 ({_, S}) ->
	      S
      end,
      split_uri(Cs)).

split_uri(URI) ->
    split_uri(URI, [{scheme, "^(([^:/?#]+):)?"},
		    {authority, "^(//([^/?#]*))?"},
		    {path, "^([^?#]*)"},
		    {'query', "^(\\?([^#]*))?"},
		    {fragment, "^(#(.*))?"}]).

split_uri("", [{Tag, _R}| T]) ->
    [{Tag, ""}| split_uri("", T)];
split_uri(Cs0, [{Tag, R}| T]) ->
    {match, 1, N} = regexp:match(Cs0, R),
    Cs1 = string:substr(Cs0, 1, N),
    Cs2 = strip_and_escape_uri_component(Tag, Cs1),
    [{Tag, Cs2}| split_uri(string:substr(Cs0, N+1), T)];
split_uri(_, []) ->
    [].

strip_and_escape_uri_component(authority, "//" ++ Cs) ->
    "//" ++ escape_uri(string:strip(Cs));
strip_and_escape_uri_component(path, Cs) ->
    escape_uri(string:strip(Cs));
strip_and_escape_uri_component('query', "?" ++ Cs) ->
    "?" ++ escape_uri(string:strip(Cs));
strip_and_escape_uri_component(fragment, "#" ++ Cs) ->
    "#" ++ escape_uri(string:strip(Cs));
strip_and_escape_uri_component(_, "") ->
    "";
strip_and_escape_uri_component(_, Cs) ->
    escape_uri(string:strip(Cs)).

escape_uri([C|Cs]) when C =< 32;
                        C == $<; C == $<; C == $#; C == $%; C == $";
                        C == $?;
			C == ${; C == $}; C ==$|; C == $\\; C == $^;
			C == $[; C == $]; C ==$';
			C >= 127 ->
    [$%, mk_hex(C div 16), mk_hex(C rem 16)| escape_uri(Cs)];
escape_uri([C|Cs]) ->
    [C|escape_uri(Cs)];
escape_uri([]) ->
    [].

mk_hex(C) when C<10 ->
    C + $0;
mk_hex(C) ->
    C - 10 + $a.

make_anchor_href(HRef) ->
    case regexp:split(HRef, "#") of
	{ok, [HRef]} ->
	    %% No `#' in HRef, i.e. only path
	    make_anchor_href(HRef, "");
	 {ok, [Path, Fragment]}->
	    make_anchor_href(Path, Fragment)
    end.

make_anchor_href(Path0, Frag0) ->
    Frag1 = string:strip(Frag0),
    Path1 = case Path0 of
		"" ->
		    "";
		_  ->
		    case regexp:match(Path0, "\.xml?\$") of
			nomatch ->
			    Path0 ++ ".html";
			_ ->
			    {ok, NewPath, _} = regexp:sub(Path0,
							  "\.xml?\$",