lib: implement new query parser
mu's query parser is the piece of software that turns your queries
into something the Xapian database can understand. So, if you query
"maildir:/inbox and subject:bla" this must be translated into a
Xapian::Query object which will retrieve the sought after messages.
Since mu's beginning, almost a decade ago, this parser was based on
Xapian's default Xapian::QueryParser. It works okay, but wasn't really
designed for the mu use-case, and had a bit of trouble with anything
that's not A..Z (think: spaces, special characters, unicode etc.).
Over the years, mu added quite a bit of pre-processing trickery to
deal with that. Still, there were corner cases and bugs that were
practically unfixable.
The solution to all of this is to have a custom query processor that
replaces Xapian's, and write it from the ground up to deal with the
special characters etc. I wrote one, as part of my "future, post-1.0
mu" reseach project, and I have now backported it to the mu 0.9.19.
From a technical perspective, this is a major cleanup, and allows us
to get rid of much of the fragile preprocessing both for indexing and
querying. From and end-user perspective this (hopefully) means that
many of the little parsing issues are gone, and it opens the way for
some new features.
From an end-user perspective:
- better support for special characters.
- regexp search! yes, you can now search for regular expressions, e.g.
subject:/h.ll?o/
will find subjects with hallo, hello, halo, philosophy, ...
As you can imagine, this can be a _heavy_ operation on the database,
and might take quite a bit longer than a normal query; but it can be
quite useful.
This commit is contained in:
128
lib/parser/tokenizer.cc
Normal file
128
lib/parser/tokenizer.cc
Normal file
@ -0,0 +1,128 @@
|
||||
/*
|
||||
** Copyright (C) 2017 Dirk-Jan C. Binnema <djcb@djcbsoftware.nl>
|
||||
**
|
||||
** This library is free software; you can redistribute it and/or
|
||||
** modify it under the terms of the GNU Lesser General Public License
|
||||
** as published by the Free Software Foundation; either version 2.1
|
||||
** of the License, or (at your option) any later version.
|
||||
**
|
||||
** This library is distributed in the hope that it will be useful,
|
||||
** but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
** MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
||||
** Lesser General Public License for more details.
|
||||
**
|
||||
** You should have received a copy of the GNU Lesser General Public
|
||||
** License along with this library; if not, write to the Free
|
||||
** Software Foundation, 51 Franklin Street, Fifth Floor, Boston, MA
|
||||
** 02110-1301, USA.
|
||||
*/
|
||||
|
||||
#include "tokenizer.hh"
|
||||
#include <cctype>
|
||||
#include <iostream>
|
||||
#include <algorithm>
|
||||
|
||||
using namespace Mux;
|
||||
|
||||
static bool
|
||||
is_separator (char c)
|
||||
{
|
||||
const auto seps = std::string (":()\"");
|
||||
|
||||
if (isblank(c))
|
||||
return true;
|
||||
else
|
||||
return seps.find(c) != std::string::npos;
|
||||
}
|
||||
|
||||
|
||||
static Mux::Token
|
||||
op_or_value (size_t pos, const std::string& val)
|
||||
{
|
||||
auto s = val;
|
||||
std::transform(s.begin(), s.end(), s.begin(), ::tolower);
|
||||
|
||||
if (s == "and")
|
||||
return Token{pos, Token::Type::And, val};
|
||||
else if (s == "or")
|
||||
return Token{pos, Token::Type::Or, val};
|
||||
else if (s == "xor")
|
||||
return Token{pos, Token::Type::Xor, val};
|
||||
else if (s == "not")
|
||||
return Token{pos, Token::Type::Not, val};
|
||||
else
|
||||
return Token{pos, Token::Type::Data, val};
|
||||
}
|
||||
|
||||
static void
|
||||
unread_char (std::string& food, char kar, size_t& pos)
|
||||
{
|
||||
food = kar + food;
|
||||
--pos;
|
||||
}
|
||||
|
||||
static Mux::Token
|
||||
eat_token (std::string& food, size_t& pos)
|
||||
{
|
||||
bool quoted{};
|
||||
bool escaped{};
|
||||
std::string value {};
|
||||
|
||||
while (!food.empty()) {
|
||||
|
||||
const auto kar = food[0];
|
||||
food.erase(0, 1);
|
||||
++pos;
|
||||
|
||||
if (kar == '\\') {
|
||||
escaped = !escaped;
|
||||
if (escaped)
|
||||
continue;
|
||||
}
|
||||
|
||||
if (kar == '"' && !escaped && quoted)
|
||||
return Token{pos, Token::Type::Data, value};
|
||||
|
||||
if (!quoted && !escaped && is_separator(kar)) {
|
||||
|
||||
if (!value.empty() && kar != ':') {
|
||||
unread_char (food, kar, pos);
|
||||
return op_or_value(pos, value);
|
||||
}
|
||||
|
||||
if (kar == '"')
|
||||
quoted = true;
|
||||
|
||||
if (quoted || isblank(kar))
|
||||
continue;
|
||||
|
||||
switch (kar) {
|
||||
case '(': return {pos, Token::Type::Open, "("};
|
||||
case ')': return {pos, Token::Type::Close,")"};
|
||||
default: break;
|
||||
}
|
||||
}
|
||||
|
||||
value += kar;
|
||||
escaped = false;
|
||||
}
|
||||
|
||||
return {pos, Token::Type::Data, value};
|
||||
}
|
||||
|
||||
|
||||
Mux::Tokens
|
||||
Mux::tokenize (const std::string& s)
|
||||
{
|
||||
Tokens tokens{};
|
||||
std::string food{s};
|
||||
size_t pos{0};
|
||||
|
||||
if (s.empty())
|
||||
return {};
|
||||
|
||||
while (!food.empty())
|
||||
tokens.emplace_back(eat_token (food, pos));
|
||||
|
||||
return tokens;
|
||||
}
|
||||
Reference in New Issue
Block a user