diff options
Diffstat (limited to 'libbuild2/functions-string.cxx')
| -rw-r--r-- | libbuild2/functions-string.cxx | 313 |
1 files changed, 298 insertions, 15 deletions
diff --git a/libbuild2/functions-string.cxx b/libbuild2/functions-string.cxx index b430ebf..b7e0a17 100644 --- a/libbuild2/functions-string.cxx +++ b/libbuild2/functions-string.cxx @@ -8,18 +8,148 @@ using namespace std; namespace build2 { + static string + replace (string&& s, value&& fv, value&& tv, optional<names>&& fs) + { + bool ic (false), fo (false), lo (false); + if (fs) + { + for (name& f: *fs) + { + string s (convert<string> (move (f))); + + if (s == "icase") + ic = true; + else if (s == "first_only") + fo = true; + else if (s == "last_only") + lo = true; + else + throw invalid_argument ("invalid flag '" + s + '\''); + } + } + + string f (convert<string> (move (fv))); + string t (convert<string> (move (tv))); + + if (f.empty ()) + throw invalid_argument ("empty <from> substring"); + + if (!s.empty ()) + { + // Note that we don't cache s.size () since the string size will be + // changing as we are replacing. In fact, we may end up with an empty + // string after a replacement. + + size_t fn (f.size ()); + + // Look for the substring forward in the [p, n) range. + // + auto find = [&s, &f, fn, ic] (size_t p) -> size_t + { + for (size_t n (s.size ()); p != n; ++p) + { + if (n - p >= fn && + (ic + ? icasecmp (f, s.c_str () + p, fn) + : s.compare (p, fn, f)) == 0) + return p; + } + + return string::npos; + }; + + // Look for the substring backard in the [0, n) range. + // + auto rfind = [&s, &f, fn, ic] (size_t n) -> size_t + { + if (n >= fn) + { + n -= fn; // Don't consider characters out of range. + + for (size_t p (n);; ) + { + if ((ic + ? icasecmp (f, s.c_str () + p, fn) + : s.compare (p, fn, f)) == 0) + return p; + + if (--p == 0) + break; + } + } + + return string::npos; + }; + + if (fo || lo) + { + size_t p (lo ? rfind (s.size ()) : find (0)); + + if (fo && lo && p != string::npos) + { + if (p != find (0)) + p = string::npos; + } + + if (p != string::npos) + s.replace (p, fn, t); + } + else + { + for (size_t p (0); (p = find (0)) != string::npos; p += fn) + s.replace (p, fn, t); + } + } + + return move (s); + } + + static size_t + find_index (const strings& vs, value&& v, optional<names>&& fs) + { + bool ic (false); + if (fs) + { + for (name& f: *fs) + { + string s (convert<string> (move (f))); + + if (s == "icase") + ic = true; + else + throw invalid_argument ("invalid flag '" + s + '\''); + } + } + + auto i (find_if (vs.begin (), vs.end (), + [ic, y = convert<string> (move (v))] (const string& x) + { + return (ic ? icasecmp (x, y) : x.compare (y)) == 0; + })); + + return i != vs.end () ? i - vs.begin () : vs.size (); + } + void string_functions (function_map& m) { function_family f (m, "string"); - f["string"] += [](string s) {return s;}; - - // @@ Shouldn't it concatenate elements into the single string? - // @@ Doesn't seem to be used so far. Can consider removing. + // Note: leave undocumented since there is no good reason for the user to + // call this function (which would be converting string to string). + // + // Note that we must handle NULL values (relied upon by the parser + // to provide conversion semantics consistent with untyped values). // - // f["string"] += [](strings v) {return v;}; + f["string"] += [](string* s) + { + return s != nullptr ? move (*s) : string (); + }; + // $string.icasecmp(<untyped>, <untyped>) + // $icasecmp(<string>, <string>) + // // Compare ASCII strings ignoring case and returning the boolean value. // f["icasecmp"] += [](string x, string y) @@ -43,7 +173,43 @@ namespace build2 convert<string> (move (y))) == 0; }; - // Trim. + // $string.replace(<untyped>, <from>, <to> [, <flags>]) + // $replace(<string>, <from>, <to> [, <flags>]) + // + // Replace occurences of substring <from> with <to> in a string. The + // <from> substring must not be empty. + // + // The following flags are supported: + // + // icase - compare ignoring case + // + // first_only - only replace the first match + // + // last_only - only replace the last match + // + // + // If both `first_only` and `last_only` flags are specified, then <from> + // is replaced only if it occurs in the string once. + // + // See also `$regex.replace()`. + // + f["replace"] += [](string s, value f, value t, optional<names> fs) + { + return replace (move (s), move (f), move (t), move (fs)); + }; + + f[".replace"] += [](names s, value f, value t, optional<names> fs) + { + return names { + name ( + replace ( + convert<string> (move (s)), move (f), move (t), move (fs)))}; + }; + + // $string.trim(<untyped>) + // $trim(<string>) + // + // Trim leading and trailing whitespaces in a string. // f["trim"] += [](string s) { @@ -55,7 +221,12 @@ namespace build2 return names {name (trim (convert<string> (move (s))))}; }; - // Convert ASCII strings into lower/upper case. + // $string.lcase(<untyped>) + // $string.ucase(<untyped>) + // $lcase(<string>) + // $ucase(<string>) + // + // Convert ASCII string into lower/upper case. // f["lcase"] += [](string s) { @@ -77,23 +248,135 @@ namespace build2 return names {name (ucase (convert<string> (move (s))))}; }; + // $size(<strings>) + // $size(<string-set>) + // $size(<string-map>) + // $size(<string>) + // + // First three forms: return the number of elements in the sequence. + // + // Fourth form: return the number of characters (bytes) in the string. + // + f["size"] += [] (strings v) {return v.size ();}; + f["size"] += [] (set<string> v) {return v.size ();}; + f["size"] += [] (map<string, string> v) {return v.size ();}; + f["size"] += [] (string v) {return v.size ();}; + + // $sort(<strings> [, <flags>]) + // + // Sort strings in ascending order. + // + // The following flags are supported: + // + // icase - sort ignoring case + // + // dedup - in addition to sorting also remove duplicates + // + f["sort"] += [](strings v, optional<names> fs) + { + bool ic (false); + bool dd (false); + if (fs) + { + for (name& f: *fs) + { + string s (convert<string> (move (f))); + + if (s == "icase") + ic = true; + else if (s == "dedup") + dd = true; + else + throw invalid_argument ("invalid flag '" + s + '\''); + } + } + + sort (v.begin (), v.end (), + [ic] (const string& x, const string& y) + { + return (ic ? icasecmp (x, y) : x.compare (y)) < 0; + }); + + if (dd) + v.erase (unique (v.begin(), v.end(), + [ic] (const string& x, const string& y) + { + return (ic ? icasecmp (x, y) : x.compare (y)) == 0; + }), + v.end ()); + + return v; + }; + + // $find(<strings>, <string>[, <flags>]) + // + // Return true if the string sequence contains the specified string. + // + // The following flags are supported: + // + // icase - compare ignoring case + // + // See also `$regex.find_match()` and `$regex.find_search()`. + // + f["find"] += [](strings vs, value v, optional<names> fs) + { + return find_index (vs, move (v), move (fs)) != vs.size (); + }; + + // $find_index(<strings>, <string>[, <flags>]) + // + // Return the index of the first element in the string sequence that + // is equal to the specified string or `$size(strings)` if none is + // found. + // + // The following flags are supported: + // + // icase - compare ignoring case + // + f["find_index"] += [](strings vs, value v, optional<names> fs) + { + return find_index (vs, move (v), move (fs)); + }; + + // $keys(<string-map>) + // + // Return the list of keys in a string map. + // + // Note that the result is sorted in ascending order. + // + f["keys"] += [](map<string, string> v) + { + strings r; + r.reserve (v.size ()); + for (pair<const string, string>& p: v) + r.push_back (p.first); // @@ PERF: use C++17 map::extract() to steal. + return r; + }; + // String-specific overloads from builtins. // function_family b (m, "builtin"); - b[".concat"] += [](string l, string r) {l += r; return l;}; + // Note that we must handle NULL values (relied upon by the parser to + // provide concatenation semantics consistent with untyped values). + // + b[".concat"] += [](string* l, string* r) + { + return l != nullptr + ? r != nullptr ? move (*l += *r) : move (*l) + : r != nullptr ? move (*r) : string (); + }; - b[".concat"] += [](string l, names ur) + b[".concat"] += [](string* l, names* ur) { - l += convert<string> (move (ur)); - return l; + string r (ur != nullptr ? convert<string> (move (*ur)) : string ()); + return l != nullptr ? move (*l += r) : move (r); }; - b[".concat"] += [](names ul, string r) + b[".concat"] += [](names* ul, string* r) { - string l (convert<string> (move (ul))); - l += r; - return l; + string l (ul != nullptr ? convert<string> (move (*ul)) : string ()); + return r != nullptr ? move (l += *r) : move (l); }; } } |