[gentoo-portage-dev] [PATCH] emerge: add --search-fuzzy and --search-fuzzy-cutoff options (bug 65566)

[Zac Medico]

Add --search-fuzzy option, with adjustable similarity ratio cutoff that
defaults to 0.8 (80% similarity).

X-Gentoo-bug: 65566
X-Gentoo-bug-url: https://bugs.gentoo.org/show_bug.cgi?id=65566
---
 man/emerge.1           | 13 ++++++++++++-
 pym/_emerge/actions.py |  6 ++++--
 pym/_emerge/main.py    | 32 +++++++++++++++++++++++++++++++-
 pym/_emerge/search.py  | 25 +++++++++++++++++++++++--
 4 files changed, 70 insertions(+), 6 deletions(-)

diff --git a/man/emerge.1 b/man/emerge.1
index bfa2f73..2727ccb 100644
--- a/man/emerge.1
+++ b/man/emerge.1
@@ -1,4 +1,4 @@
-.TH "EMERGE" "1" "Feb 2016" "Portage VERSION" "Portage"
+.TH "EMERGE" "1" "Apr 2016" "Portage VERSION" "Portage"
 .SH "NAME"
 emerge \- Command\-line interface to the Portage system
 .SH "SYNOPSIS"
@@ -854,6 +854,17 @@ If ebuilds using EAPIs which \fIdo not\fR support \fBHDEPEND\fR are built in
 the same \fBemerge\fR run as those using EAPIs which \fIdo\fR support
 \fBHDEPEND\fR, this option affects only the former.
 .TP
+.BR "\-\-search\-fuzzy [ y | n ]"
+Enable or disable fuzzy search for search actions.
+.TP
+.BR "\-\-search\-fuzzy\-cutoff CUTOFF"
+Set similarity ratio cutoff (a floating-point number between 0 and 1).
+Results with similarity ratios lower than the cutoff are discarded.
+This option has no effect unless the \fB\-\-search\-fuzzy\fR option
+is enabled.
+.br
+Defaults to 0.8 (80% similarity).
+.TP
 .BR "\-\-search\-index < y | n >"
 Enable or disable indexed search for search actions. This option is
 enabled by default. The search index needs to be regenerated by
diff --git a/pym/_emerge/actions.py b/pym/_emerge/actions.py
index 59626ad..caae79a 100644
--- a/pym/_emerge/actions.py
+++ b/pym/_emerge/actions.py
@@ -1,4 +1,4 @@
-# Copyright 1999-2015 Gentoo Foundation
+# Copyright 1999-2016 Gentoo Foundation
 # Distributed under the terms of the GNU General Public License v2
 
 from __future__ import division, print_function, unicode_literals
@@ -1955,7 +1955,9 @@ def action_search(root_config, myopts, myfiles, spinner):
 			spinner, "--searchdesc" in myopts,
 			"--quiet" not in myopts, "--usepkg" in myopts,
 			"--usepkgonly" in myopts,
-			search_index = myopts.get("--search-index", "y") != "n")
+			search_index=myopts.get("--search-index", "y") != "n",
+			fuzzy=myopts.get("--search-fuzzy", False),
+			fuzzy_cutoff=myopts.get("--search-fuzzy-cutoff"))
 		for mysearch in myfiles:
 			try:
 				searchinstance.execute(mysearch)
diff --git a/pym/_emerge/main.py b/pym/_emerge/main.py
index 5dbafee..06c385e 100644
--- a/pym/_emerge/main.py
+++ b/pym/_emerge/main.py
@@ -1,4 +1,4 @@
-# Copyright 1999-2015 Gentoo Foundation
+# Copyright 1999-2016 Gentoo Foundation
 # Distributed under the terms of the GNU General Public License v2
 
 from __future__ import print_function
@@ -156,6 +156,7 @@ def insert_optional_args(args):
 		'--rebuild-if-unbuilt'   : y_or_n,
 		'--rebuilt-binaries'     : y_or_n,
 		'--root-deps'  : ('rdeps',),
+		'--search-fuzzy'         : y_or_n,
 		'--select'               : y_or_n,
 		'--selective'            : y_or_n,
 		"--use-ebuild-visibility": y_or_n,
@@ -647,6 +648,16 @@ def parse_opts(tmpcmdline, silent=False):
 			"choices" :("True", "rdeps")
 		},
 
+		"--search-fuzzy": {
+			"help": "Enable or disable fuzzy search",
+			"choices": true_y_or_n
+		},
+
+		"--search-fuzzy-cutoff": {
+			"help": "Set similarity ratio cutoff (a floating-point number between 0 and 1)",
+			"action": "store"
+		},
+
 		"--search-index": {
 			"help": "Enable or disable indexed search (enabled by default)",
 			"choices": y_or_n
@@ -908,6 +919,11 @@ def parse_opts(tmpcmdline, silent=False):
 	if myoptions.root_deps in true_y:
 		myoptions.root_deps = True
 
+	if myoptions.search_fuzzy in true_y:
+		myoptions.search_fuzzy = True
+	else:
+		myoptions.search_fuzzy = None
+
 	if myoptions.select in true_y:
 		myoptions.select = True
 		myoptions.oneshot = False
@@ -1000,6 +1016,20 @@ def parse_opts(tmpcmdline, silent=False):
 
 		myoptions.rebuilt_binaries_timestamp = rebuilt_binaries_timestamp
 
+	if myoptions.search_fuzzy_cutoff:
+		try:
+			fuzzy_cutoff = float(myoptions.search_fuzzy_cutoff)
+		except ValueError:
+			fuzzy_cutoff = 0.0
+
+		if fuzzy_cutoff <= 0.0:
+			fuzzy_cutoff = None
+			if not silent:
+				parser.error("Invalid --search-fuzzy-cutoff parameter: '%s'\n" % \
+					(myoptions.search_fuzzy_cutoff,))
+
+		myoptions.search_fuzzy_cutoff = fuzzy_cutoff
+
 	if myoptions.use_ebuild_visibility in true_y:
 		myoptions.use_ebuild_visibility = True
 	else:
diff --git a/pym/_emerge/search.py b/pym/_emerge/search.py
index 32d326e..3210854 100644
--- a/pym/_emerge/search.py
+++ b/pym/_emerge/search.py
@@ -1,8 +1,9 @@
-# Copyright 1999-2015 Gentoo Foundation
+# Copyright 1999-2016 Gentoo Foundation
 # Distributed under the terms of the GNU General Public License v2
 
 from __future__ import unicode_literals
 
+import difflib
 import re
 import portage
 from portage import os
@@ -28,7 +29,8 @@ class search(object):
 	# public interface
 	#
 	def __init__(self, root_config, spinner, searchdesc,
-		verbose, usepkg, usepkgonly, search_index=True):
+		verbose, usepkg, usepkgonly, search_index=True,
+		fuzzy=False, fuzzy_cutoff=None):
 		"""Searches the available and installed packages for the supplied search key.
 		The list of available and installed packages is created at object instantiation.
 		This makes successive searches faster."""
@@ -42,6 +44,8 @@ class search(object):
 		self.spinner = None
 		self.root_config = root_config
 		self.setconfig = root_config.setconfig
+		self.fuzzy = fuzzy
+		self.fuzzy_cutoff = 0.8 if fuzzy_cutoff is None else fuzzy_cutoff
 		self.matches = {"pkg" : []}
 		self.mlen = 0
 
@@ -248,11 +252,26 @@ class search(object):
 		if self.searchkey.startswith('@'):
 			match_category = 1
 			self.searchkey = self.searchkey[1:]
+		fuzzy = False
 		if regexsearch:
 			self.searchre=re.compile(self.searchkey,re.I)
 		else:
 			self.searchre=re.compile(re.escape(self.searchkey), re.I)
 
+			# Fuzzy search does not support regular expressions, therefore
+			# it is disabled for regular expression searches.
+			if self.fuzzy:
+				fuzzy = True
+				cutoff = self.fuzzy_cutoff
+				seq_match = difflib.SequenceMatcher()
+				seq_match.set_seq2(self.searchkey.lower())
+
+				def fuzzy_search(match_string):
+					seq_match.set_seq1(match_string.lower())
+					return (seq_match.real_quick_ratio() >= cutoff and
+						seq_match.quick_ratio() >= cutoff and
+						seq_match.ratio() >= cutoff)
+
 		for package in self._cp_all():
 			self._spinner_update()
 
@@ -280,6 +299,8 @@ class search(object):
 					continue
 
 				yield ("desc", package)
+			elif fuzzy and fuzzy_search(match_string):
+				yield ("pkg", package)
 
 		self.sdict = self.setconfig.getSets()
 		for setname in self.sdict:
-- 
2.7.4