build/src/util/regex.jam

# Copyright 2001, 2002 Dave Abrahams
# Copyright 2003 Douglas Gregor
# Copyright 2003 Rene Rivera
# Copyright 2002, 2003, 2004, 2005 Vladimir Prus
# Distributed under the Boost Software License, Version 1.0.
# (See accompanying file LICENSE_1_0.txt or http://www.boost.org/LICENSE_1_0.txt)

#
#   Returns a list of the following substrings:
#   1) from beginning till the first occurrence of 'separator' or till the end,
#   2) between each occurrence of 'separator' and the next occurrence,
#   3) from the last occurrence of 'separator' till the end.
#   If no separator is present, the result will contain only one element.
#

rule split ( string separator )
{
    local result ;
    local s = $(string) ;

    # Break pieaces off 's' until it has no separators left.
    local match = 1 ;
    while $(match)
    {
        match = [ MATCH ^(.*)($(separator))(.*) : $(s) ] ;
        if $(match)
        {
            match += "" ;  # in case 3rd item was empty - works around MATCH bug
            result = $(match[3]) $(result) ;
            s = $(match[1]) ;
        }
    }
    # Combine the remaining part at the beginning, which does not have
    # separators, with the pieces broken off. Note that the rule's signature
    # does not allow the initial s to be empty.
    return $(s) $(result) ;
}


# Returns the concatenated results of Applying regex.split to every element of
# the list using the separator pattern.
#
rule split-list ( list * : separator )
{
    local result ;
    for s in $(list)
    {
        result += [ split $(s) $(separator) ] ;
    }
    return $(result) ;
}


# Match string against pattern, and return the elements indicated by indices.
#
rule match ( pattern : string : indices * )
{
    indices ?= 1 2 3 4 5 6 7 8 9 ;
    local x = [ MATCH $(pattern) : $(string) ] ;
    return $(x[$(indices)]) ;
}


# Matches all elements of 'list' agains the 'pattern' and returns a list of
# elements indicated by indices of all successful matches. If 'indices' is
# omitted returns a list of first parenthesised groups of all successful
# matches.
#
rule transform ( list * : pattern : indices * )
{
    indices ?= 1 ;
    local result ;
    for local e in $(list)
    {
        local m = [ MATCH $(pattern) : $(e) ] ;
        if $(m)
        {
            result += $(m[$(indices)]) ;
        }
    }
    return $(result) ;
}

NATIVE_RULE regex : transform ;


# Escapes all of the characters in symbols using the escape symbol escape-symbol
# for the given string, and returns the escaped string.
#
rule escape ( string : symbols : escape-symbol )
{
    local result = "" ;
    local m = 1 ;
    while $(m)
    {
        m = [ MATCH ^([^$(symbols)]*)([$(symbols)])(.*) : $(string) ] ;
        if $(m)
        {
            m += "" ;  # Supposedly a bug fix; borrowed from regex.split
            result = "$(result)$(m[1])$(escape-symbol)$(m[2])" ;
            string = $(m[3]) ;
        }
    }
    string ?= "" ;
    result = "$(result)$(string)" ;
    return $(result) ;
}


# Replaces occurrences of a match string in a given string and returns the new
# string. The match string can be a regex expression.
#
rule replace (
    string  # The string to modify.
    match  # The characters to replace.
    replacement  # The string to replace with.
    )
{
    local result = "" ;
    local parts = 1 ;
    while $(parts)
    {
        parts = [ MATCH ^(.*)($(match))(.*) : $(string) ] ;
        if $(parts)
        {
            parts += "" ;
            result = "$(replacement)$(parts[3])$(result)" ;
            string = $(parts[1]) ;
        }
    }
    string ?= "" ;
    result = "$(string)$(result)" ;
    return $(result) ;
}


# Replaces occurrences of a match string in a given list of strings and returns
# a list of new strings. The match string can be a regex expression.
#
# list        - the list of strings to modify.
# match       - the search expression.
# replacement - the string to replace with.
#
rule replace-list ( list * : match : replacement )
{
    local result ;
    for local e in $(list)
    {
        result += [ replace $(e) $(match) $(replacement) ] ;
    }
    return $(result) ;
}


rule __test__ ( )
{
    import assert ;

    assert.result a b c : split "a/b/c" / ;
    assert.result "" a b c : split "/a/b/c" / ;
    assert.result "" "" a b c : split "//a/b/c" / ;
    assert.result "" a "" b c : split "/a//b/c" / ;
    assert.result "" a "" b c "" : split "/a//b/c/" / ;
    assert.result "" a "" b c "" "" : split "/a//b/c//" / ;

    assert.result a c b d
        : match (.)(.)(.)(.) : abcd : 1 3 2 4 ;

    assert.result a b c d
        : match (.)(.)(.)(.) : abcd ;

    assert.result ababab cddc
        : match ((ab)*)([cd]+) : abababcddc : 1 3 ;

    assert.result a.h c.h
        : transform <a.h> \"b.h\" <c.h> : <(.*)> ;

    assert.result a.h b.h c.h
        : transform <a.h> \"b.h\" <c.h> : <([^>]*)>|\"([^\"]*)\" : 1 2 ;

    assert.result "^<?xml version=\"1.0\"^>"
        : escape "<?xml version=\"1.0\">" : "&|()<>^" : "^" ;

    assert.result "<?xml version=\\\"1.0\\\">"
        : escape "<?xml version=\"1.0\">" : "\\\"" : "\\" ;

    assert.result "string&nbsp;string&nbsp;" : replace "string string " " " "&nbsp;" ;
    assert.result "&nbsp;string&nbsp;string" : replace " string string" " " "&nbsp;" ;
    assert.result "string&nbsp;&nbsp;string" : replace "string  string" " " "&nbsp;" ;
    assert.result "-" : replace "&" "&" "-" ;

    assert.result "-" "a-b" : replace-list "&" "a&b" : "&" : "-" ;
}