diff options
Diffstat (limited to 'lib/stdlib')
| -rw-r--r-- | lib/stdlib/doc/src/string.xml | 396 | ||||
| -rw-r--r-- | lib/stdlib/src/otp_internal.erl | 46 | ||||
| -rw-r--r-- | lib/stdlib/src/string.erl | 10 | ||||
| -rwxr-xr-x | lib/stdlib/uc_spec/gen_unicode_mod.escript | 24 |
4 files changed, 71 insertions, 405 deletions
diff --git a/lib/stdlib/doc/src/string.xml b/lib/stdlib/doc/src/string.xml index 9d5edd9ecf..130fc74a28 100644 --- a/lib/stdlib/doc/src/string.xml +++ b/lib/stdlib/doc/src/string.xml @@ -109,10 +109,8 @@ <p>This module has been reworked in Erlang/OTP 20 to handle <seealso marker="unicode#type-chardata"> <c>unicode:chardata()</c></seealso> and operate on grapheme - clusters. The <seealso marker="#oldapi"> <c>old - functions</c></seealso> that only work on Latin-1 lists as input - are still available but should not be - used. They will be deprecated in Erlang/OTP 21. + clusters. The <c>old functions</c> that only work on Latin-1 lists as input + are kept for backwards compatibility reasons but should not be used. </p> </description> @@ -594,7 +592,7 @@ ÖÄÅ</pre> or <c>both</c>, indicates from which direction characters are to be removed. </p> - <p> Default <c><anno>Characters</anno></c> are the set of + <p> Default <c><anno>Characters</anno></c> is the set of nonbreakable whitespace codepoints, defined as Pattern_White_Space in <url href="http://unicode.org/reports/tr31/">Unicode Standard Annex #31</url>. @@ -631,393 +629,5 @@ ÖÄÅ</pre> </func> </funcs> - - <section> - <marker id="oldapi"/> - <title>Obsolete API functions</title> - <p>Here follows the function of the old API. - These functions only work on a list of Latin-1 characters. - </p> - <note><p> - The functions are kept for backward compatibility, but are - not recommended. - They will be deprecated in Erlang/OTP 21. - </p> - <p>Any undocumented functions in <c>string</c> are not to be used.</p> - </note> - </section> - - <funcs> - <func> - <name name="centre" arity="2"/> - <name name="centre" arity="3"/> - <fsummary>Center a string.</fsummary> - <desc> - <p>Returns a string, where <c><anno>String</anno></c> is centered in the - string and surrounded by blanks or <c><anno>Character</anno></c>. - The resulting string has length <c><anno>Number</anno></c>.</p> - <p>This function is <seealso marker="#oldapi">obsolete</seealso>. - Use - <seealso marker="#pad/3"><c>pad/3</c></seealso>. - </p> - </desc> - </func> - - <func> - <name name="chars" arity="2"/> - <name name="chars" arity="3"/> - <fsummary>Return a string consisting of numbers of characters.</fsummary> - <desc> - <p>Returns a string consisting of <c><anno>Number</anno></c> characters - <c><anno>Character</anno></c>. Optionally, the string can end with - string <c><anno>Tail</anno></c>.</p> - <p>This function is <seealso marker="#oldapi">obsolete</seealso>. - Use - <seealso marker="lists#duplicate/2"><c>lists:duplicate/2</c></seealso>.</p> - </desc> - </func> - - <func> - <name name="chr" arity="2"/> - <fsummary>Return the index of the first occurrence of - a character in a string.</fsummary> - <desc> - <p>Returns the index of the first occurrence of - <c><anno>Character</anno></c> in <c><anno>String</anno></c>. Returns - <c>0</c> if <c><anno>Character</anno></c> does not occur.</p> - <p>This function is <seealso marker="#oldapi">obsolete</seealso>. - Use - <seealso marker="#find/2"><c>find/2</c></seealso>.</p> - </desc> - </func> - - <func> - <name name="concat" arity="2"/> - <fsummary>Concatenate two strings.</fsummary> - <desc> - <p>Concatenates <c><anno>String1</anno></c> and - <c><anno>String2</anno></c> to form a new string - <c><anno>String3</anno></c>, which is returned.</p> - <p> - This function is <seealso marker="#oldapi">obsolete</seealso>. - Use <c>[<anno>String1</anno>, <anno>String2</anno>]</c> as - <c>Data</c> argument, and call - <seealso marker="unicode#characters_to_list/2"> - <c>unicode:characters_to_list/2</c></seealso> or - <seealso marker="unicode#characters_to_binary/2"> - <c>unicode:characters_to_binary/2</c></seealso> - to flatten the output. - </p> - </desc> - </func> - - <func> - <name name="copies" arity="2"/> - <fsummary>Copy a string.</fsummary> - <desc> - <p>Returns a string containing <c><anno>String</anno></c> repeated - <c><anno>Number</anno></c> times.</p> - <p>This function is <seealso marker="#oldapi">obsolete</seealso>. - Use - <seealso marker="lists#duplicate/2"><c>lists:duplicate/2</c></seealso>.</p> - </desc> - </func> - - <func> - <name name="cspan" arity="2"/> - <fsummary>Span characters at start of a string.</fsummary> - <desc> - <p>Returns the length of the maximum initial segment of - <c><anno>String</anno></c>, which consists entirely of characters - not from <c><anno>Chars</anno></c>.</p> - <p>This function is <seealso marker="#oldapi">obsolete</seealso>. - Use - <seealso marker="#take/3"><c>take/3</c></seealso>.</p> - <p><em>Example:</em></p> - <code type="none"> -> string:cspan("\t abcdef", " \t"). -0</code> - </desc> - </func> - - <func> - <name name="join" arity="2"/> - <fsummary>Join a list of strings with separator.</fsummary> - <desc> - <p>Returns a string with the elements of <c><anno>StringList</anno></c> - separated by the string in <c><anno>Separator</anno></c>.</p> - <p>This function is <seealso marker="#oldapi">obsolete</seealso>. - Use - <seealso marker="lists#join/2"><c>lists:join/2</c></seealso>.</p> - <p><em>Example:</em></p> - <code type="none"> -> join(["one", "two", "three"], ", "). -"one, two, three"</code> - </desc> - </func> - - <func> - <name name="left" arity="2"/> - <name name="left" arity="3"/> - <fsummary>Adjust left end of a string.</fsummary> - <desc> - <p>Returns <c><anno>String</anno></c> with the length adjusted in - accordance with <c><anno>Number</anno></c>. The left margin is - fixed. If <c>length(<anno>String</anno>)</c> < - <c><anno>Number</anno></c>, then <c><anno>String</anno></c> is padded - with blanks or <c><anno>Character</anno></c>s.</p> - <p>This function is <seealso marker="#oldapi">obsolete</seealso>. - Use - <seealso marker="#pad/2"><c>pad/2</c></seealso> or - <seealso marker="#pad/3"><c>pad/3</c></seealso>.</p> - <p><em>Example:</em></p> - <code type="none"> -> string:left("Hello",10,$.). -"Hello....."</code> - </desc> - </func> - - <func> - <name name="len" arity="1"/> - <fsummary>Return the length of a string.</fsummary> - <desc> - <p>Returns the number of characters in <c><anno>String</anno></c>.</p> - <p>This function is <seealso marker="#oldapi">obsolete</seealso>. - Use - <seealso marker="#length/1"><c>length/1</c></seealso>.</p> - </desc> - </func> - - <func> - <name name="rchr" arity="2"/> - <fsummary>Return the index of the last occurrence of - a character in a string.</fsummary> - <desc> - <p>Returns the index of the last occurrence of - <c><anno>Character</anno></c> in <c><anno>String</anno></c>. Returns - <c>0</c> if <c><anno>Character</anno></c> does not occur.</p> - <p>This function is <seealso marker="#oldapi">obsolete</seealso>. - Use - <seealso marker="#find/3"><c>find/3</c></seealso>.</p> - </desc> - </func> - - <func> - <name name="right" arity="2"/> - <name name="right" arity="3"/> - <fsummary>Adjust right end of a string.</fsummary> - <desc> - <p>Returns <c><anno>String</anno></c> with the length adjusted in - accordance with <c><anno>Number</anno></c>. The right margin is - fixed. If the length of <c>(<anno>String</anno>)</c> < - <c><anno>Number</anno></c>, then <c><anno>String</anno></c> is padded - with blanks or <c><anno>Character</anno></c>s.</p> - <p>This function is <seealso marker="#oldapi">obsolete</seealso>. - Use - <seealso marker="#pad/3"><c>pad/3</c></seealso>.</p> - <p><em>Example:</em></p> - <code type="none"> -> string:right("Hello", 10, $.). -".....Hello"</code> - </desc> - </func> - - <func> - <name name="rstr" arity="2"/> - <fsummary>Find the index of a substring.</fsummary> - <desc> - <p>Returns the position where the last occurrence of - <c><anno>SubString</anno></c> begins in <c><anno>String</anno></c>. - Returns <c>0</c> if <c><anno>SubString</anno></c> - does not exist in <c><anno>String</anno></c>.</p> - <p>This function is <seealso marker="#oldapi">obsolete</seealso>. - Use - <seealso marker="#find/3"><c>find/3</c></seealso>.</p> - <p><em>Example:</em></p> - <code type="none"> -> string:rstr(" Hello Hello World World ", "Hello World"). -8</code> - </desc> - </func> - - <func> - <name name="span" arity="2"/> - <fsummary>Span characters at start of a string.</fsummary> - <desc> - <p>Returns the length of the maximum initial segment of - <c><anno>String</anno></c>, which consists entirely of characters - from <c><anno>Chars</anno></c>.</p> - <p>This function is <seealso marker="#oldapi">obsolete</seealso>. - Use - <seealso marker="#take/2"><c>take/2</c></seealso>.</p> - <p><em>Example:</em></p> - <code type="none"> -> string:span("\t abcdef", " \t"). -5</code> - </desc> - </func> - - <func> - <name name="str" arity="2"/> - <fsummary>Find the index of a substring.</fsummary> - <desc> - <p>Returns the position where the first occurrence of - <c><anno>SubString</anno></c> begins in <c><anno>String</anno></c>. - Returns <c>0</c> if <c><anno>SubString</anno></c> - does not exist in <c><anno>String</anno></c>.</p> - <p>This function is <seealso marker="#oldapi">obsolete</seealso>. - Use - <seealso marker="#find/2"><c>find/2</c></seealso>.</p> - <p><em>Example:</em></p> - <code type="none"> -> string:str(" Hello Hello World World ", "Hello World"). -8</code> - </desc> - </func> - - <func> - <name name="strip" arity="1"/> - <name name="strip" arity="2"/> - <name name="strip" arity="3"/> - <fsummary>Strip leading or trailing characters.</fsummary> - <desc> - <p>Returns a string, where leading or trailing, or both, blanks or a - number of <c><anno>Character</anno></c> have been removed. - <c><anno>Direction</anno></c>, which can be <c>left</c>, <c>right</c>, - or <c>both</c>, indicates from which direction blanks are to be - removed. <c>strip/1</c> is equivalent to - <c>strip(String, both)</c>.</p> - <p>This function is <seealso marker="#oldapi">obsolete</seealso>. - Use - <seealso marker="#trim/3"><c>trim/3</c></seealso>.</p> - <p><em>Example:</em></p> - <code type="none"> -> string:strip("...Hello.....", both, $.). -"Hello"</code> - </desc> - </func> - - <func> - <name name="sub_string" arity="2"/> - <name name="sub_string" arity="3"/> - <fsummary>Extract a substring.</fsummary> - <desc> - <p>Returns a substring of <c><anno>String</anno></c>, starting at - position <c><anno>Start</anno></c> to the end of the string, or to - and including position <c><anno>Stop</anno></c>.</p> - <p>This function is <seealso marker="#oldapi">obsolete</seealso>. - Use - <seealso marker="#slice/3"><c>slice/3</c></seealso>.</p> - <p><em>Example:</em></p> - <code type="none"> -sub_string("Hello World", 4, 8). -"lo Wo"</code> - </desc> - </func> - - <func> - <name name="substr" arity="2"/> - <name name="substr" arity="3"/> - <fsummary>Return a substring of a string.</fsummary> - <desc> - <p>Returns a substring of <c><anno>String</anno></c>, starting at - position <c><anno>Start</anno></c>, and ending at the end of the - string or at length <c><anno>Length</anno></c>.</p> - <p>This function is <seealso marker="#oldapi">obsolete</seealso>. - Use - <seealso marker="#slice/3"><c>slice/3</c></seealso>.</p> - <p><em>Example:</em></p> - <code type="none"> -> substr("Hello World", 4, 5). -"lo Wo"</code> - </desc> - </func> - - <func> - <name name="sub_word" arity="2"/> - <name name="sub_word" arity="3"/> - <fsummary>Extract subword.</fsummary> - <desc> - <p>Returns the word in position <c><anno>Number</anno></c> of - <c><anno>String</anno></c>. Words are separated by blanks or - <c><anno>Character</anno></c>s.</p> - <p>This function is <seealso marker="#oldapi">obsolete</seealso>. - Use - <seealso marker="#nth_lexeme/3"><c>nth_lexeme/3</c></seealso>.</p> - <p><em>Example:</em></p> - <code type="none"> -> string:sub_word(" Hello old boy !",3,$o). -"ld b"</code> - </desc> - </func> - - <func> - <name name="to_lower" arity="1" clause_i="1"/> - <name name="to_lower" arity="1" clause_i="2"/> - <name name="to_upper" arity="1" clause_i="1"/> - <name name="to_upper" arity="1" clause_i="2"/> - <fsummary>Convert case of string (ISO/IEC 8859-1).</fsummary> - <type variable="String" name_i="1"/> - <type variable="Result" name_i="1"/> - <type variable="Char"/> - <type variable="CharResult"/> - <desc> - <p>The specified string or character is case-converted. Notice that - the supported character set is ISO/IEC 8859-1 (also called Latin 1); - all values outside this set are unchanged</p> - <p>This function is <seealso marker="#oldapi">obsolete</seealso> use - <seealso marker="#lowercase/1"><c>lowercase/1</c></seealso>, - <seealso marker="#uppercase/1"><c>uppercase/1</c></seealso>, - <seealso marker="#titlecase/1"><c>titlecase/1</c></seealso> or - <seealso marker="#casefold/1"><c>casefold/1</c></seealso>.</p> - </desc> - </func> - - <func> - <name name="tokens" arity="2"/> - <fsummary>Split string into tokens.</fsummary> - <desc> - <p>Returns a list of tokens in <c><anno>String</anno></c>, separated - by the characters in <c><anno>SeparatorList</anno></c>.</p> - <p><em>Example:</em></p> - <code type="none"> -> tokens("abc defxxghix jkl", "x "). -["abc", "def", "ghi", "jkl"]</code> - <p>Notice that, as shown in this example, two or more - adjacent separator characters in <c><anno>String</anno></c> - are treated as one. That is, there are no empty - strings in the resulting list of tokens.</p> - <p>This function is <seealso marker="#oldapi">obsolete</seealso>. - Use - <seealso marker="#lexemes/2"><c>lexemes/2</c></seealso>.</p> - </desc> - </func> - - <func> - <name name="words" arity="1"/> - <name name="words" arity="2"/> - <fsummary>Count blank separated words.</fsummary> - <desc> - <p>Returns the number of words in <c><anno>String</anno></c>, separated - by blanks or <c><anno>Character</anno></c>.</p> - <p>This function is <seealso marker="#oldapi">obsolete</seealso>. - Use - <seealso marker="#lexemes/2"><c>lexemes/2</c></seealso>.</p> - <p><em>Example:</em></p> - <code type="none"> -> words(" Hello old boy!", $o). -4</code> - </desc> - </func> - </funcs> - - <section> - <title>Notes</title> - <p>Some of the general string functions can seem to overlap each - other. The reason is that this string package is the - combination of two earlier packages and all functions of - both packages have been retained.</p> - </section> - </erlref> diff --git a/lib/stdlib/src/otp_internal.erl b/lib/stdlib/src/otp_internal.erl index 9e9c0dc413..b547657a7f 100644 --- a/lib/stdlib/src/otp_internal.erl +++ b/lib/stdlib/src/otp_internal.erl @@ -615,6 +615,52 @@ obsolete_1(filename, find_src, 2) -> obsolete_1(erlang, hash, 2) -> {removed, {erlang, phash2, 2}, "20.0"}; +%% Added in OTP-21 +obsolete_1(string, len, 1) -> + {deprecated, "deprecated; use string:length/3 instead"}; +obsolete_1(string, concat, 2) -> + {deprecated, "deprecated; use [Str1,Str2] instead"}; +obsolete_1(string, str, 2) -> + {deprecated, "deprecated; use string:find/2 instead"}; +obsolete_1(string, rstr, 2) -> + {deprecated, "deprecated; use string:find/3 instead"}; +obsolete_1(string, chr, 2) -> + {deprecated, "deprecated; use string:find/2 instead"}; +obsolete_1(string, rchr, 2) -> + {deprecated, "deprecated; use string:find/3 instead"}; +obsolete_1(string, span, 2) -> + {deprecated, "deprecated; use string:take/2 instead"}; +obsolete_1(string, cspan, 2) -> + {deprecated, "deprecated; use string:take/3 instead"}; +obsolete_1(string, substr, _) -> + {deprecated, "deprecated; use string:slice/3 instead"}; +obsolete_1(string, tokens, 2) -> + {deprecated, "deprecated; use string:lexemes/2 instead"}; +obsolete_1(string, chars, _) -> + {deprecated, "deprecated; use lists:duplicate/2 instead"}; +obsolete_1(string, copies, _) -> + {deprecated, "deprecated; use lists:duplicate/2 instead"}; +obsolete_1(string, words, _) -> + {deprecated, "deprecated; use string:lexemes/2 instead"}; +obsolete_1(string, strip, _) -> + {deprecated, "deprecated; use string:trim/3 instead"}; +obsolete_1(string, sub_word, _) -> + {deprecated, "deprecated; use string:nth_lexeme/3 instead"}; +obsolete_1(string, sub_string, _) -> + {deprecated, "deprecated; use string:slice/3 instead"}; +obsolete_1(string, left, _) -> + {deprecated, "deprecated; use string:pad/3 instead"}; +obsolete_1(string, right, _) -> + {deprecated, "deprecated; use string:pad/3 instead"}; +obsolete_1(string, centre, _) -> + {deprecated, "deprecated; use string:pad/3 instead"}; +obsolete_1(string, join, _) -> + {deprecated, "deprecated; use lists:join/2 instead"}; +obsolete_1(string, to_upper, _) -> + {deprecated, "deprecated; use string:uppercase/1 or string:titlecase/1 instead"}; +obsolete_1(string, to_lower, _) -> + {deprecated, "deprecated; use string:lowercase/1 or string:casefold/1 instead"}; + %% not obsolete obsolete_1(_, _, _) -> diff --git a/lib/stdlib/src/string.erl b/lib/stdlib/src/string.erl index 4972da297d..5a4d2df2a6 100644 --- a/lib/stdlib/src/string.erl +++ b/lib/stdlib/src/string.erl @@ -87,6 +87,16 @@ %%% May be removed -export([list_to_float/1, list_to_integer/1]). +-deprecated([{len,1},{concat,2}, + {str,2},{chr,2},{rchr,2},{rstr,2}, + {span,2},{cspan,2},{substr,'_'},{tokens,2}, + {chars,'_'}, + {copies,2},{words,'_'},{strip,'_'}, + {sub_word,'_'},{left,'_'},{right,'_'}, + {sub_string,'_'},{centre,'_'},{join,2}, + {to_upper,1}, {to_lower,1} + ]). + %% Uses bifs: string:list_to_float/1 and string:list_to_integer/1 -spec list_to_float(String) -> {Float, Rest} | {'error', Reason} when String :: string(), diff --git a/lib/stdlib/uc_spec/gen_unicode_mod.escript b/lib/stdlib/uc_spec/gen_unicode_mod.escript index fefd7d3b70..0b32852b6e 100755 --- a/lib/stdlib/uc_spec/gen_unicode_mod.escript +++ b/lib/stdlib/uc_spec/gen_unicode_mod.escript @@ -65,7 +65,7 @@ main(_) -> %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% parse_unicode_data(Line0, Acc) -> - Line = string:strip(Line0, right, $\n), + Line = string:chomp(Line0), [CodePoint,Name,_Cat,Class,_BiDi,Decomp, _N1,_N2,_N3,_BDMirror,_Uni1,_Iso|Case] = tokens(Line, ";"), {Dec,Comp} = case to_decomp(Decomp) of @@ -78,14 +78,14 @@ parse_unicode_data(Line0, Acc) -> |Acc]. to_class(String) -> - list_to_integer(string:strip(String, both)). + list_to_integer(string:trim(String, both)). to_decomp("") -> []; to_decomp("<" ++ Str) -> - [Tag,Rest] = string:tokens(Str, ">"), + [Tag,Rest] = string:lexemes(Str, ">"), {list_to_atom(Tag), to_decomp(Rest)}; to_decomp(CodePoints) -> - CPL = string:tokens(CodePoints, " "), + CPL = string:lexemes(CodePoints, " "), [hex_to_int(CP) || CP <- CPL]. to_case(["","",""]) -> []; @@ -105,20 +105,20 @@ parse_special_casing(Line, Table) -> array:set(CP, Entry#cp{cs=Case}, Table). to_scase([Lower,Title,Upper|_]) -> - {unlist([hex_to_int(CP) || CP <- string:strip(string:tokens(Upper, " "), both)]), - unlist([hex_to_int(CP) || CP <- string:strip(string:tokens(Lower, " "), both)]), - unlist([hex_to_int(CP) || CP <- string:strip(string:tokens(Title, " "), both)]), + {unlist([hex_to_int(CP) || CP <- string:lexemes(Upper, " ")]), + unlist([hex_to_int(CP) || CP <- string:lexemes(Lower, " ")]), + unlist([hex_to_int(CP) || CP <- string:lexemes(Title, " ")]), []}. parse_case_folding(Line, Table) -> [CodePoint, Class0, CaseStr |_Comments] = tokens(Line, ";"), - Class = string:strip(Class0, both), + Class = string:trim(Class0, both), if Class =:= "T" -> Table; %% Do not support localization yet Class =:= "S" -> Table; %% Ignore simple true -> CP = hex_to_int(CodePoint), Case = unlist([hex_to_int(CPC) || - CPC <- string:strip(string:tokens(CaseStr, " "), both)]), + CPC <- string:lexemes(CaseStr, " ")]), #cp{cs={U,L,T,_}} = Entry = array:get(CP, Table), array:set(CP, Entry#cp{cs={U,L,T,Case}}, Table) end. @@ -869,10 +869,10 @@ optimize_ranges_1(Rs) -> hex_to_int([]) -> []; hex_to_int(HexStr) -> - list_to_integer(string:strip(HexStr, both), 16). + list_to_integer(string:trim(HexStr, both), 16). to_atom(Str) -> - list_to_atom(string:to_lower(string:strip(Str, both))). + list_to_atom(string:lowercase(string:trim(Str, both))). foldl(Fun, Acc, Fd) -> Get = fun() -> file:read_line(Fd) end, @@ -892,7 +892,7 @@ foldl_1(Fun, Acc, Get) -> -%% Differs from string:tokens, it returns empty string as token between two delimiters +%% Differs from string:lexemes, it returns empty string as token between two delimiters tokens(S, [C]) -> tokens(lists:reverse(S), C, []). |