search: add syntax highlighting, line numbers and line context

to file content search results
This commit is contained in:
Daniel Dourvaris 2016-05-30 07:15:12 +03:00
parent ae8c247137
commit 2fc47913e5
9 changed files with 783 additions and 7 deletions

View file

@ -18,6 +18,7 @@ module.exports = function(grunt) {
'<%= dirs.js.src %>/bootstrap.js',
'<%= dirs.js.src %>/mousetrap.js',
'<%= dirs.js.src %>/moment.js',
'<%= dirs.js.src %>/moment.js',
'<%= dirs.js.src %>/appenlight-client-0.4.1.min.js',
// Plugins
@ -27,12 +28,13 @@ module.exports = function(grunt) {
'<%= dirs.js.src %>/plugins/jquery.auto-grow-input.js',
'<%= dirs.js.src %>/plugins/jquery.autocomplete.js',
'<%= dirs.js.src %>/plugins/jquery.debounce.js',
'<%= dirs.js.src %>/plugins/jquery.mark.js',
'<%= dirs.js.src %>/plugins/jquery.timeago.js',
'<%= dirs.js.src %>/plugins/jquery.timeago-extension.js',
// Select2
'<%= dirs.js.src %>/select2/select2.js',
// Code-mirror
'<%= dirs.js.src %>/codemirror/codemirror.js',
'<%= dirs.js.src %>/codemirror/codemirror_loadmode.js',

View file

@ -79,7 +79,8 @@ class SearchController(BaseRepoController):
try:
search_result = searcher.search(
search_query, search_type, c.perm_user, repo_name)
search_query, search_type, c.perm_user, repo_name,
requested_page, page_limit)
formatted_results = Page(
search_result['results'], page=requested_page,

View file

@ -36,11 +36,14 @@ import urlparse
import time
import string
import hashlib
import pygments
from datetime import datetime
from functools import partial
from pygments.formatters.html import HtmlFormatter
from pygments import highlight as code_highlight
from pygments.lexers import (
get_lexer_by_name, get_lexer_for_filename, get_lexer_for_mimetype)
from pylons import url
from pylons.i18n.translation import _, ungettext
from pyramid.threadlocal import get_current_request
@ -307,6 +310,176 @@ class CodeHtmlFormatter(HtmlFormatter):
yield 0, '</td></tr></table>'
class SearchContentCodeHtmlFormatter(CodeHtmlFormatter):
def __init__(self, **kw):
# only show these line numbers if set
self.only_lines = kw.pop('only_line_numbers', [])
self.query_terms = kw.pop('query_terms', [])
self.max_lines = kw.pop('max_lines', 5)
self.line_context = kw.pop('line_context', 3)
self.url = kw.pop('url', None)
super(CodeHtmlFormatter, self).__init__(**kw)
def _wrap_code(self, source):
for cnt, it in enumerate(source):
i, t = it
t = '<pre>%s</pre>' % t
yield i, t
def _wrap_tablelinenos(self, inner):
yield 0, '<table class="code-highlight %stable">' % self.cssclass
last_shown_line_number = 0
current_line_number = 1
for t, line in inner:
if not t:
yield t, line
continue
if current_line_number in self.only_lines:
if last_shown_line_number + 1 != current_line_number:
yield 0, '<tr>'
yield 0, '<td class="line">...</td>'
yield 0, '<td id="hlcode" class="code"></td>'
yield 0, '</tr>'
yield 0, '<tr>'
if self.url:
yield 0, '<td class="line"><a href="%s#L%i">%i</a></td>' % (
self.url, current_line_number, current_line_number)
else:
yield 0, '<td class="line"><a href="">%i</a></td>' % (
current_line_number)
yield 0, '<td id="hlcode" class="code">' + line + '</td>'
yield 0, '</tr>'
last_shown_line_number = current_line_number
current_line_number += 1
yield 0, '</table>'
def extract_phrases(text_query):
"""
Extracts phrases from search term string making sure phrases
contained in double quotes are kept together - and discarding empty values
or fully whitespace values eg.
'some text "a phrase" more' => ['some', 'text', 'a phrase', 'more']
"""
in_phrase = False
buf = ''
phrases = []
for char in text_query:
if in_phrase:
if char == '"': # end phrase
phrases.append(buf)
buf = ''
in_phrase = False
continue
else:
buf += char
continue
else:
if char == '"': # start phrase
in_phrase = True
phrases.append(buf)
buf = ''
continue
elif char == ' ':
phrases.append(buf)
buf = ''
continue
else:
buf += char
phrases.append(buf)
phrases = [phrase.strip() for phrase in phrases if phrase.strip()]
return phrases
def get_matching_offsets(text, phrases):
"""
Returns a list of string offsets in `text` that the list of `terms` match
>>> get_matching_offsets('some text here', ['some', 'here'])
[(0, 4), (10, 14)]
"""
offsets = []
for phrase in phrases:
for match in re.finditer(phrase, text):
offsets.append((match.start(), match.end()))
return offsets
def normalize_text_for_matching(x):
"""
Replaces all non alnum characters to spaces and lower cases the string,
useful for comparing two text strings without punctuation
"""
return re.sub(r'[^\w]', ' ', x.lower())
def get_matching_line_offsets(lines, terms):
""" Return a set of `lines` indices (starting from 1) matching a
text search query, along with `context` lines above/below matching lines
:param lines: list of strings representing lines
:param terms: search term string to match in lines eg. 'some text'
:param context: number of lines above/below a matching line to add to result
:param max_lines: cut off for lines of interest
eg.
>>> get_matching_line_offsets('''
words words words
words words words
some text some
words words words
words words words
text here what
''', 'text', context=1)
{3: [(5, 9)], 6: [(0, 4)]]
"""
matching_lines = {}
phrases = [normalize_text_for_matching(phrase)
for phrase in extract_phrases(terms)]
for line_index, line in enumerate(lines, start=1):
match_offsets = get_matching_offsets(
normalize_text_for_matching(line), phrases)
if match_offsets:
matching_lines[line_index] = match_offsets
return matching_lines
def get_lexer_safe(mimetype=None, filepath=None):
"""
Tries to return a relevant pygments lexer using mimetype/filepath name,
defaulting to plain text if none could be found
"""
lexer = None
try:
if mimetype:
lexer = get_lexer_for_mimetype(mimetype)
if not lexer:
lexer = get_lexer_for_filename(path)
except pygments.util.ClassNotFound:
pass
if not lexer:
lexer = get_lexer_by_name('text')
return lexer
def pygmentize(filenode, **kwargs):
"""
pygmentize function using pygments

View file

@ -90,7 +90,8 @@ class Search(BaseSearch):
if self.searcher:
self.searcher.close()
def search(self, query, document_type, search_user, repo_name=None):
def search(self, query, document_type, search_user, repo_name=None,
requested_page=1, page_limit=10):
log.debug(u'QUERY: %s on %s', query, document_type)
result = {
'results': [],

View file

@ -514,6 +514,26 @@ div.search-code-body {
.match { background-color: #faffa6;}
.break { display: block; width: 100%; background-color: #DDE7EF; color: #747474; }
}
.code-highlighttable {
border-collapse: collapse;
tr:hover {
background: #fafafa;
}
td.code {
padding-left: 10px;
}
td.line {
border-right: 1px solid #ccc !important;
padding-right: 10px;
text-align: right;
font-family: "Lucida Console",Monaco,monospace;
span {
white-space: pre-wrap;
color: #666666;
}
}
}
}
div.annotatediv { margin-left: 2px; margin-right: 4px; }

View file

@ -0,0 +1,490 @@
/*!***************************************************
* mark.js v6.1.0
* https://github.com/julmot/mark.js
* Copyright (c) 20142016, Julian Motz
* Released under the MIT license https://git.io/vwTVl
*****************************************************/
"use strict";
var _extends = Object.assign || function (target) { for (var i = 1; i < arguments.length; i++) { var source = arguments[i]; for (var key in source) { if (Object.prototype.hasOwnProperty.call(source, key)) { target[key] = source[key]; } } } return target; };
var _createClass = function () { function defineProperties(target, props) { for (var i = 0; i < props.length; i++) { var descriptor = props[i]; descriptor.enumerable = descriptor.enumerable || false; descriptor.configurable = true; if ("value" in descriptor) descriptor.writable = true; Object.defineProperty(target, descriptor.key, descriptor); } } return function (Constructor, protoProps, staticProps) { if (protoProps) defineProperties(Constructor.prototype, protoProps); if (staticProps) defineProperties(Constructor, staticProps); return Constructor; }; }();
var _typeof = typeof Symbol === "function" && typeof Symbol.iterator === "symbol" ? function (obj) { return typeof obj; } : function (obj) { return obj && typeof Symbol === "function" && obj.constructor === Symbol ? "symbol" : typeof obj; };
function _classCallCheck(instance, Constructor) { if (!(instance instanceof Constructor)) { throw new TypeError("Cannot call a class as a function"); } }
(function (factory, window, document) {
if (typeof define === "function" && define.amd) {
define(["jquery"], function (jQuery) {
return factory(window, document, jQuery);
});
} else if ((typeof exports === "undefined" ? "undefined" : _typeof(exports)) === "object") {
factory(window, document, require("jquery"));
} else {
factory(window, document, jQuery);
}
})(function (window, document, $) {
var Mark = function () {
function Mark(ctx) {
_classCallCheck(this, Mark);
this.ctx = ctx;
}
_createClass(Mark, [{
key: "log",
value: function log(msg) {
var level = arguments.length <= 1 || arguments[1] === undefined ? "debug" : arguments[1];
var log = this.opt.log;
if (!this.opt.debug) {
return;
}
if ((typeof log === "undefined" ? "undefined" : _typeof(log)) === "object" && typeof log[level] === "function") {
log[level]("mark.js: " + msg);
}
}
}, {
key: "escapeStr",
value: function escapeStr(str) {
return str.replace(/[\-\[\]\/\{\}\(\)\*\+\?\.\\\^\$\|]/g, "\\$&");
}
}, {
key: "createRegExp",
value: function createRegExp(str) {
str = this.escapeStr(str);
if (Object.keys(this.opt.synonyms).length) {
str = this.createSynonymsRegExp(str);
}
if (this.opt.diacritics) {
str = this.createDiacriticsRegExp(str);
}
str = this.createAccuracyRegExp(str);
return str;
}
}, {
key: "createSynonymsRegExp",
value: function createSynonymsRegExp(str) {
var syn = this.opt.synonyms;
for (var index in syn) {
if (syn.hasOwnProperty(index)) {
var value = syn[index],
k1 = this.escapeStr(index),
k2 = this.escapeStr(value);
str = str.replace(new RegExp("(" + k1 + "|" + k2 + ")", "gmi"), "(" + k1 + "|" + k2 + ")");
}
}
return str;
}
}, {
key: "createDiacriticsRegExp",
value: function createDiacriticsRegExp(str) {
var dct = ["aÀÁÂÃÄÅàáâãäåĀāąĄ", "cÇçćĆčČ", "dđĐďĎ", "eÈÉÊËèéêëěĚĒēęĘ", "iÌÍÎÏìíîïĪī", "lłŁ", "nÑñňŇńŃ", "oÒÓÔÕÕÖØòóôõöøŌō", "rřŘ", "sŠšśŚ", "tťŤ", "uÙÚÛÜùúûüůŮŪū", "yŸÿýÝ", "zŽžżŻźŹ"];
var handled = [];
str.split("").forEach(function (ch) {
dct.every(function (dct) {
if (dct.indexOf(ch) !== -1) {
if (handled.indexOf(dct) > -1) {
return false;
}
str = str.replace(new RegExp("[" + dct + "]", "gmi"), "[" + dct + "]");
handled.push(dct);
}
return true;
});
});
return str;
}
}, {
key: "createAccuracyRegExp",
value: function createAccuracyRegExp(str) {
switch (this.opt.accuracy) {
case "partially":
return "()(" + str + ")";
case "complementary":
return "()(\\S*" + str + "\\S*)";
case "exactly":
return "(^|\\s)(" + str + ")(?=\\s|$)";
}
}
}, {
key: "getSeparatedKeywords",
value: function getSeparatedKeywords(sv) {
var _this = this;
var stack = [];
sv.forEach(function (kw) {
if (!_this.opt.separateWordSearch) {
if (kw.trim()) {
stack.push(kw);
}
} else {
kw.split(" ").forEach(function (kwSplitted) {
if (kwSplitted.trim()) {
stack.push(kwSplitted);
}
});
}
});
return {
"keywords": stack,
"length": stack.length
};
}
}, {
key: "getElements",
value: function getElements() {
var ctx = void 0,
stack = [];
if (typeof this.ctx === "undefined") {
ctx = [];
} else if (this.ctx instanceof HTMLElement) {
ctx = [this.ctx];
} else if (Array.isArray(this.ctx)) {
ctx = this.ctx;
} else {
ctx = Array.prototype.slice.call(this.ctx);
}
ctx.forEach(function (ctx) {
stack.push(ctx);
var childs = ctx.querySelectorAll("*");
if (childs.length) {
stack = stack.concat(Array.prototype.slice.call(childs));
}
});
if (!ctx.length) {
this.log("Empty context", "warn");
}
return {
"elements": stack,
"length": stack.length
};
}
}, {
key: "matches",
value: function matches(el, selector) {
return (el.matches || el.matchesSelector || el.msMatchesSelector || el.mozMatchesSelector || el.webkitMatchesSelector || el.oMatchesSelector).call(el, selector);
}
}, {
key: "matchesFilter",
value: function matchesFilter(el, exclM) {
var _this2 = this;
var remain = true;
var fltr = this.opt.filter.concat(["script", "style", "title"]);
if (!this.opt.iframes) {
fltr = fltr.concat(["iframe"]);
}
if (exclM) {
fltr = fltr.concat(["*[data-markjs='true']"]);
}
fltr.every(function (filter) {
if (_this2.matches(el, filter)) {
return remain = false;
}
return true;
});
return !remain;
}
}, {
key: "onIframeReady",
value: function onIframeReady(ifr, successFn, errorFn) {
try {
(function () {
var ifrWin = ifr.contentWindow,
bl = "about:blank",
compl = "complete";
var callCallback = function callCallback() {
try {
if (ifrWin.document === null) {
throw new Error("iframe inaccessible");
}
successFn(ifrWin.document);
} catch (e) {
errorFn();
}
};
var isBlank = function isBlank() {
var src = ifr.getAttribute("src").trim(),
href = ifrWin.location.href;
return href === bl && src !== bl && src;
};
var observeOnload = function observeOnload() {
var listener = function listener() {
try {
if (!isBlank()) {
ifr.removeEventListener("load", listener);
callCallback();
}
} catch (e) {
errorFn();
}
};
ifr.addEventListener("load", listener);
};
if (ifrWin.document.readyState === compl) {
if (isBlank()) {
observeOnload();
} else {
callCallback();
}
} else {
observeOnload();
}
})();
} catch (e) {
errorFn();
}
}
}, {
key: "forEachElementInIframe",
value: function forEachElementInIframe(ifr, cb) {
var _this3 = this;
var end = arguments.length <= 2 || arguments[2] === undefined ? function () {} : arguments[2];
var open = 0;
var checkEnd = function checkEnd() {
if (--open < 1) {
end();
}
};
this.onIframeReady(ifr, function (con) {
var stack = Array.prototype.slice.call(con.querySelectorAll("*"));
if ((open = stack.length) === 0) {
checkEnd();
}
stack.forEach(function (el) {
if (el.tagName.toLowerCase() === "iframe") {
(function () {
var j = 0;
_this3.forEachElementInIframe(el, function (iel, len) {
cb(iel, len);
if (len - 1 === j) {
checkEnd();
}
j++;
}, checkEnd);
})();
} else {
cb(el, stack.length);
checkEnd();
}
});
}, function () {
var src = ifr.getAttribute("src");
_this3.log("iframe '" + src + "' could not be accessed", "warn");
checkEnd();
});
}
}, {
key: "forEachElement",
value: function forEachElement(cb) {
var _this4 = this;
var end = arguments.length <= 1 || arguments[1] === undefined ? function () {} : arguments[1];
var exclM = arguments.length <= 2 || arguments[2] === undefined ? true : arguments[2];
var _getElements = this.getElements();
var stack = _getElements.elements;
var open = _getElements.length;
var checkEnd = function checkEnd() {
if (--open === 0) {
end();
}
};
checkEnd(++open);
stack.forEach(function (el) {
if (!_this4.matchesFilter(el, exclM)) {
if (el.tagName.toLowerCase() === "iframe") {
_this4.forEachElementInIframe(el, function (iel) {
if (!_this4.matchesFilter(iel, exclM)) {
cb(iel);
}
}, checkEnd);
return;
} else {
cb(el);
}
}
checkEnd();
});
}
}, {
key: "forEachNode",
value: function forEachNode(cb) {
var end = arguments.length <= 1 || arguments[1] === undefined ? function () {} : arguments[1];
this.forEachElement(function (n) {
for (n = n.firstChild; n; n = n.nextSibling) {
if (n.nodeType === 3 && n.textContent.trim()) {
cb(n);
}
}
}, end);
}
}, {
key: "wrapMatches",
value: function wrapMatches(node, regex, custom, cb) {
var hEl = !this.opt.element ? "mark" : this.opt.element,
index = custom ? 0 : 2;
var match = void 0;
while ((match = regex.exec(node.textContent)) !== null) {
var pos = match.index;
if (!custom) {
pos += match[index - 1].length;
}
var startNode = node.splitText(pos);
node = startNode.splitText(match[index].length);
if (startNode.parentNode !== null) {
var repl = document.createElement(hEl);
repl.setAttribute("data-markjs", "true");
if (this.opt.className) {
repl.setAttribute("class", this.opt.className);
}
repl.textContent = match[index];
startNode.parentNode.replaceChild(repl, startNode);
cb(repl);
}
regex.lastIndex = 0;
}
}
}, {
key: "unwrapMatches",
value: function unwrapMatches(node) {
var parent = node.parentNode;
var docFrag = document.createDocumentFragment();
while (node.firstChild) {
docFrag.appendChild(node.removeChild(node.firstChild));
}
parent.replaceChild(docFrag, node);
parent.normalize();
}
}, {
key: "markRegExp",
value: function markRegExp(regexp, opt) {
var _this5 = this;
this.opt = opt;
this.log("Searching with expression \"" + regexp + "\"");
var found = false;
var eachCb = function eachCb(element) {
found = true;
_this5.opt.each(element);
};
this.forEachNode(function (node) {
_this5.wrapMatches(node, regexp, true, eachCb);
}, function () {
if (!found) {
_this5.opt.noMatch(regexp);
}
_this5.opt.complete();
_this5.opt.done();
});
}
}, {
key: "mark",
value: function mark(sv, opt) {
var _this6 = this;
this.opt = opt;
sv = typeof sv === "string" ? [sv] : sv;
var _getSeparatedKeywords = this.getSeparatedKeywords(sv);
var kwArr = _getSeparatedKeywords.keywords;
var kwArrLen = _getSeparatedKeywords.length;
if (kwArrLen === 0) {
this.opt.complete();
this.opt.done();
}
kwArr.forEach(function (kw) {
var regex = new RegExp(_this6.createRegExp(kw), "gmi"),
found = false;
var eachCb = function eachCb(element) {
found = true;
_this6.opt.each(element);
};
_this6.log("Searching with expression \"" + regex + "\"");
_this6.forEachNode(function (node) {
_this6.wrapMatches(node, regex, false, eachCb);
}, function () {
if (!found) {
_this6.opt.noMatch(kw);
}
if (kwArr[kwArrLen - 1] === kw) {
_this6.opt.complete();
_this6.opt.done();
}
});
});
}
}, {
key: "unmark",
value: function unmark(opt) {
var _this7 = this;
this.opt = opt;
var sel = this.opt.element ? this.opt.element : "*";
sel += "[data-markjs]";
if (this.opt.className) {
sel += "." + this.opt.className;
}
this.log("Removal selector \"" + sel + "\"");
this.forEachElement(function (el) {
if (_this7.matches(el, sel)) {
_this7.unwrapMatches(el);
}
}, function () {
_this7.opt.complete();
_this7.opt.done();
}, false);
}
}, {
key: "opt",
set: function set(val) {
this._opt = _extends({}, {
"element": "",
"className": "",
"filter": [],
"iframes": false,
"separateWordSearch": true,
"diacritics": true,
"synonyms": {},
"accuracy": "partially",
"each": function each() {},
"noMatch": function noMatch() {},
"done": function done() {},
"complete": function complete() {},
"debug": false,
"log": window.console
}, val);
},
get: function get() {
return this._opt;
}
}]);
return Mark;
}();
$.fn.mark = function (sv, opt) {
new Mark(this).mark(sv, opt);
return this;
};
$.fn.markRegExp = function (regexp, opt) {
new Mark(this).markRegExp(regexp, opt);
return this;
};
$.fn.unmark = function (opt) {
new Mark(this).unmark(opt);
return this;
};
}, window, document);

View file

@ -33,7 +33,7 @@
</div>
</td>
<td data-commit-id="${h.md5_safe(entry['repository'])+entry['commit_id']}" id="c-${h.md5_safe(entry['repository'])+entry['commit_id']}" class="message td-description open">
%if entry['message_hl']:
%if entry.get('message_hl'):
${h.literal(entry['message_hl'])}
%else:
${h.urlify_commit_message(entry['message'], entry['repository'])}

View file

@ -1,3 +1,40 @@
<%def name="highlight_text_file(terms, text, url, line_context=3,
max_lines=10,
mimetype=None, filepath=None)">
<%
lines = text.split('\n')
lines_of_interest = set()
matching_lines = h.get_matching_line_offsets(lines, terms)
shown_matching_lines = 0
for line_number in matching_lines:
if len(lines_of_interest) < max_lines:
lines_of_interest |= set(range(
max(line_number - line_context, 0),
min(line_number + line_context, len(lines))))
shown_matching_lines += 1
%>
${h.code_highlight(
text,
h.get_lexer_safe(
mimetype=mimetype,
filepath=filepath,
),
h.SearchContentCodeHtmlFormatter(
linenos=True,
cssclass="code-highlight",
url=url,
query_terms=terms,
only_line_numbers=lines_of_interest
))|n}
%if len(matching_lines) > shown_matching_lines:
<a href="${url}">
${len(matching_lines) - shown_matching_lines} ${_('more matches in this file')}
</p>
%endif
</%def>
<div class="search-results">
%for entry in c.formatted_results:
## search results are additionally filtered, and this check is just a safe gate
@ -29,7 +66,7 @@
<div class="buttons">
<a id="file_history_overview_full" href="${h.url('changelog_file_home',repo_name=entry.get('repository',''),revision=entry.get('commit_id', 'tip'),f_path=entry.get('f_path',''))}">
${_('Show Full History')}
</a> |
</a> |
${h.link_to(_('Annotation'), h.url('files_annotate_home', repo_name=entry.get('repository',''),revision=entry.get('commit_id', 'tip'),f_path=entry.get('f_path','')))}
| ${h.link_to(_('Raw'), h.url('files_raw_home', repo_name=entry.get('repository',''),revision=entry.get('commit_id', 'tip'),f_path=entry.get('f_path','')))}
| <a href="${h.url('files_rawfile_home',repo_name=entry.get('repository',''),revision=entry.get('commit_id', 'tip'),f_path=entry.get('f_path',''))}">
@ -38,8 +75,10 @@
</div>
</div>
<div class="code-body search-code-body">
<pre>${h.literal(entry['content_short_hl'])}</pre>
</div>
${highlight_text_file(c.cur_query, entry['content'],
url=h.url('files_home',repo_name=entry['repository'],revision=entry.get('commit_id', 'tip'),f_path=entry['f_path']),
mimetype=entry.get('mimetype'), filepath=entry.get('path'))}
</div>
</div>
% endif
%endfor
@ -49,3 +88,14 @@
${c.formatted_results.pager('$link_previous ~2~ $link_next')}
</div>
%endif
%if c.cur_query:
<script type="text/javascript">
$(function(){
$(".code").mark(
'${' '.join(h.normalize_text_for_matching(c.cur_query).split())}',
{"className": 'match',
});
})
</script>
%endif

View file

@ -155,3 +155,42 @@ def test_get_visual_attr(pylonsapp):
def test_chop_at(test_text, inclusive, expected_text):
assert helpers.chop_at_smart(
test_text, '\n', inclusive, '...') == expected_text
@pytest.mark.parametrize('test_text, expected_output', [
('some text', ['some', 'text']),
('some text', ['some', 'text']),
('some text "with a phrase"', ['some', 'text', 'with a phrase']),
('"a phrase" "another phrase"', ['a phrase', 'another phrase']),
('"justphrase"', ['justphrase']),
('""', []),
('', []),
(' ', []),
('" "', []),
])
def test_extract_phrases(test_text, expected_output):
assert helpers.extract_phrases(test_text) == expected_output
@pytest.mark.parametrize('test_text, text_phrases, expected_output', [
('some text here', ['some', 'here'], [(0, 4), (10, 14)]),
('here here there', ['here'], [(0, 4), (5, 9), (11, 15)]),
('irrelevant', ['not found'], []),
('irrelevant', ['not found'], []),
])
def test_get_matching_offsets(test_text, text_phrases, expected_output):
assert helpers.get_matching_offsets(
test_text, text_phrases) == expected_output
def test_normalize_text_for_matching():
assert helpers.normalize_text_for_matching(
'OJjfe)*#$*@)$JF*)3r2f80h') == 'ojjfe jf 3r2f80h'
def test_get_matching_line_offsets():
assert helpers.get_matching_line_offsets([
'words words words',
'words words words',
'some text some',
'words words words',
'words words words',
'text here what'], 'text') == {3: [(5, 9)], 6: [(0, 4)]}