def rebuildsearchobjectviasearchorder(so: SearchObject) -> SearchObject:
"""
rewrite the searchobject so that you look for the less common things first
"""
if so.lemmaone and so.lemmatwo:
hwone = querytotalwordcounts(so.lemmaone.dictionaryentry)
hwtwo = querytotalwordcounts(so.lemmatwo.dictionaryentry)
# from server.hipparchiaobjects.wordcountobjects import dbWordCountObject
# print('{a}: {b}, {c}: {d}'.format(a=so.lemmaone.dictionaryentry, b=hwone.t, c=so.lemmatwo.dictionaryentry, d=hwtwo.t))
if hwtwo.t < hwone.t:
tmp = so.lemmaone
so.lemmaone = so.lemmatwo
so.lemmatwo = tmp
elif so.lemma or so.proximatelemma:
pass
elif so.accented or re.search(r'^[a-z]', so.termone) and so.near:
# choose the necessarily faster option
unomdifiedskg = massagesearchtermsforwhitespace(so.seeking)
unmodifiedprx = so.proximate
leastcommon = findleastcommonterm(unomdifiedskg + ' ' + unmodifiedprx,
so.accented)
if leastcommon != unomdifiedskg:
tmp = so.termone
so.termone = so.termtwo
so.termtwo = tmp
elif len(so.termtwo) > len(so.termone) and so.near:
# look for the longest word first since that is probably the quicker route
# but you can't swap searchingfor and proximate this way in a 'is not near' search without yielding the wrong focus
tmp = so.termone
so.termone = so.termtwo
so.termtwo = tmp
return so
def precomposedsqlphrasesearch(so: SearchObject) -> List[dbWorkLine]:
"""
you are searching for a relatively rare word: we will keep things simple-ish
note that the second half of this is not MP: but searches already only take 6s; so clean code probably wins here
FIXME:
can't find the phrases in here...:
κατεϲκεύαϲεν τὸ ἐνϲόριον FAILS
ϲεν τὸ ἐνϲόριον το SUCCEEDS
ch0005w001/2749
1 Ῥουφεῖνα Ἰουδαία ἀρχι-
2 ϲυνάγωγοϲ κατεϲκεύα-
3 ϲεν τὸ ἐνϲόριον τοῖϲ ἀπε- ( match: ἀπελευθέροιϲ )
4 λευθέροιϲ καὶ θρέμ(μ)αϲιν
5 μηδενὸϲ ἄλ(λ)ου ἐξουϲίαν ἔ-
actually, this is a BUILDER problem AND a SERVER problem:
BUILDER:
2749 does not have κατεϲκεύαϲεν in it
hipparchiaDB=# select index, accented_line, hyphenated_words from ch0005 where index between 2746 and 2752;
index | accented_line | hyphenated_words
-------+-----------------------------------+------------------
2748 | ῥουφεῖνα ἰουδαία ἀρχιϲυνάγωγοϲ | ἀρχιϲυνάγωγοϲ
2749 | κατεϲκεύα- |
2750 | ϲεν τὸ ἐνϲόριον τοῖϲ ἀπελευθέροιϲ | ἀπελευθέροιϲ
2751 | καὶ θρέμμαϲιν |
2752 | μηδενὸϲ ἄλλου ἐξουϲίαν ἔχοντοϲ | ἔχοντοϲ
(5 rows)
SERVER: ἀπελευθέροιϲ καὶ θρέμμαϲιν is missed by precomposedsqlphrasesearch()
but it is found by precomposedsqlsubqueryphrasesearch()
maybe it is time to nuke precomposedsqlphrasesearch() after all...
NB: the dynamic workonphrasesearch() CAN find 'ἀπελευθέροιϲ καὶ θρέμμαϲιν'
"""
debugmessage('executing a precomposedsqlphrasesearch()')
so.termone = so.leastcommon
searchphrase = so.phrase
phraselen = len(searchphrase.split(' '))
initialhitlines = generatepreliminaryhitlist(so)
m = 'Now searching among the {h} initial hits for the full phrase "{p}"'
so.poll.statusis(m.format(h=so.poll.gethits(), p=so.originalseeking))
so.poll.sethits(0)
fullmatches = list()
dbconnection = ConnectionObject()
dbcursor = dbconnection.cursor()
commitcount = 0
while initialhitlines and len(fullmatches) <= so.cap:
commitcount += 1
if commitcount == hipparchia.config['MPCOMMITCOUNT']:
dbconnection.commit()
commitcount = 0
hit = initialhitlines.pop()
wordset = lookoutsideoftheline(hit.index, phraselen - 1, hit.authorid, so, dbcursor)
if not so.accented:
wordset = re.sub(r'[.?!;:,·’]', str(), wordset)
else:
# the difference is in the apostrophe: δ vs δ’
wordset = re.sub(r'[.?!;:,·]', str(), wordset)
if so.near and re.search(searchphrase, wordset):
fullmatches.append(hit)
so.poll.addhits(1)
elif not so.near and re.search(searchphrase, wordset) is None:
fullmatches.append(hit)
so.poll.addhits(1)
dbconnection.connectioncleanup()
return fullmatches
def precomposedphraseandproximitysearch(so: SearchObject) -> List[dbWorkLine]:
"""
do a precomposedsqlsubqueryphrasesearch() and then search inside the results for part two...
corner case tester: two line-enders: non solum + temporum dignitatem
[12] Caesar, De Bello Gallico: book 7, chapter 54, section 4, line 2
7.54.3.3 multatos agris, omnibus ereptis sociis, imposito stipendio,
7.54.4.1 obsidibus summa cum contumelia extortis, et quam in
7.54.4.2 fortunam quamque in amplitudinem deduxisset, ut non
7.54.4.3 solum in pristinum statum redissent, sed omnium tem-
7.54.4.4 porum dignitatem et gratiam antecessisse viderentur.
corner case tester: two distant line-enders: temporum dignitatem + obsides Galliae
ut non
solum in pristinum statum redissent, sed omnium tem- 7.54.4.3
porum dignitatem et gratiam antecessisse viderentur.
his datis mandatis eos ab se dimisit.
Noviodunum erat oppidum Haeduorum ad ripas 7.55.1.1
Ligeris opportuno loco positum. huc Caesar omnes ob- 7.55.2.1
sides Galliae, frumentum, pecuniam publicam, suorum
the old code will trick you by pretending it is doing a valid search even though it is not really set up
to handle this situation and was not supposed to promise that it could do phrase+
[it's the phrase-spanning-two-lines bit that yields the problem since you do "lemma+" but have no handler for
the multi-line issue]
0.0.0-1.8.1
Sought all 19 known forms of »χώρα« within 1 lines of »μεγάλην δύναμιν«
Searched 3,182 works and found 1 passage (0.77s)
Searched between 850 B.C.E. and 300 B.C.E.
Sorted by name
[1] Ctesias, Fragmenta: Volume-Jacoby#-F 3c,688,F, fragment 5, line 47
3c,688,F.5.45 τόπουϲ. (3) γενόμενον δ’ ἀποϲτάτην καὶ πείϲαντα τὸ ϲύμπαν ἔθνοϲ ἀντέχεϲθαι
3c,688,F.5.46 τῆϲ ἐλευθερίαϲ, αἱρεθῆναι ϲτρατηγὸν διὰ τὴν ἀνδρείαν. ἔπειτα πυνθανόμενον
3c,688,F.5.47 ἀθροιζομένην ἐπ’ αὐτὸν μεγάλην δύναμιν, καθοπλίϲαι τοὺϲ Καδουϲίουϲ παν-
3c,688,F.5.48 δημεί, καὶ καταϲτρατοπεδεῦϲαι πρὸϲ ταῖϲ εἰϲ τὴν χώραν εἰϲβολαῖϲ, ἔχοντα
3c,688,F.5.49 τοὺϲ ϲύμπανταϲ οὐκ ἐλάττουϲ εἴκοϲι μυριάδων. (4) τοῦ δὲ βαϲιλέωϲ Ἀρταίου
1.8.2+
Sought all 19 known forms of »χώρα« within 1 lines of »μεγάλην δύναμιν«
Searched 2,346 works and found 2 passages (2.2s)
Searched between 850 B.C.E. and 300 B.C.E.
Sorted by name
[1] Ctesias, Fragmenta: Volume-Jacoby#-F 3c,688,F, fragment 5, line 47
3c,688,F.5.45 τόπουϲ. (3) γενόμενον δ’ ἀποϲτάτην καὶ πείϲαντα τὸ ϲύμπαν ἔθνοϲ ἀντέχεϲθαι
3c,688,F.5.46 τῆϲ ἐλευθερίαϲ, αἱρεθῆναι ϲτρατηγὸν διὰ τὴν ἀνδρείαν. ἔπειτα πυνθανόμενον
3c,688,F.5.47 ἀθροιζομένην ἐπ’ αὐτὸν μεγάλην δύναμιν, καθοπλίϲαι τοὺϲ Καδουϲίουϲ παν-
3c,688,F.5.48 δημεί, καὶ καταϲτρατοπεδεῦϲαι πρὸϲ ταῖϲ εἰϲ τὴν χώραν εἰϲβολαῖϲ, ἔχοντα
3c,688,F.5.49 τοὺϲ ϲύμπανταϲ οὐκ ἐλάττουϲ εἴκοϲι μυριάδων. (4) τοῦ δὲ βαϲιλέωϲ Ἀρταίου
[2] Ctesias, Fragmenta: Volume-Jacoby#-F 3c,688,F, fragment 14, line 54
3c,688,F.14.52 (40) καὶ ἐλυπήθη λύπην ϲφοδρὰν Μεγάβυζοϲ, καὶ ἐπένθηϲε, καὶ ἠιτήϲατο
3c,688,F.14.53 ἐπὶ Ϲυρίαν τὴν ἑαυτοῦ χώραν ἀπιέναι. ἐνταῦθα λάθραι καὶ τοὺϲ ἄλλουϲ τῶν
3c,688,F.14.54 Ἑλλήνων προέπεμπε. καὶ ἀπήιει, καὶ ἀπέϲτη βαϲιλέωϲ, καὶ ἀθροίζει μεγάλην
3c,688,F.14.55 δύναμιν ἄχρι πεντεκαίδεκα μυριάδων χωρὶϲ τῶν ἱππέων [καὶ τῶν πεζῶν].
3c,688,F.14.56 καὶ πέμπεται Οὔϲιριϲ κατ’ αὐτοῦ ϲὺν ⟨κ⟩ μυριάϲι, καὶ ϲυνάπτεται πόλεμοϲ, καὶ
"""
#
# initially do "within x lines"
#
phrasefinder = re.compile(r'[^\s]\s[^\s]')
if re.search(phrasefinder, so.seeking) and re.search(
phrasefinder, so.proximate):
secondsearch = precomposedsqlsubqueryphrasesearch
elif not re.search(phrasefinder, so.seeking) and re.search(
phrasefinder, so.proximate):
so.swapseekingandproxmate()
so.swaplemmaoneandtwo()
secondsearch = basicprecomposedsqlsearcher
else:
secondsearch = basicprecomposedsqlsearcher
c = so.cap
ps = so.proximate
so.proximate = str()
pl = so.lemmatwo
so.lemmatwo = str()
so.phrase = so.seeking
firstterm = so.phrase
so.cap = hipparchia.config['INTERMEDIATESEARCHCAP']
initialhitlines = precomposedsqlsubqueryphrasesearch(so)
so.seeking = ps
so.lemmaone = pl
so.setsearchtype()
so.cap = c
if secondsearch == precomposedsqlsubqueryphrasesearch:
so.phrase = ps
else:
so.phrase = str()
so = perparesoforsecondsqldict(so, initialhitlines)
so.searchsqldict = searchlistintosqldict(so, so.seeking)
if so.lemmaone:
so.searchsqldict = rewritesqlsearchdictforlemmata(so)
so.poll.sethits(0)
newhitlines = secondsearch(so)
initialhitlinedict = {hl.uniqueid: hl for hl in initialhitlines}
newhitlineids = set()
for nhl in newhitlines:
indices = list(
range(nhl.index - so.distance, nhl.index + so.distance + 1))
ids = ['{a}_{b}'.format(a=nhl.wkuinversalid, b=i) for i in indices]
newhitlineids.update(ids)
maybefinalhitines = list()
if so.near:
# "is near"
maybefinalhitines = [
initialhitlinedict[hl] for hl in initialhitlinedict
if hl in newhitlineids
]
elif not so.near:
# "is not near"
maybefinalhitines = [
initialhitlinedict[hl] for hl in initialhitlinedict
if hl not in newhitlineids
]
#
# if neccessary, do "within x words" as x lines hits will always be a subset of the first set
#
if so.lemmaone:
secondterm = wordlistintoregex(so.lemmaone.formlist)
else:
secondterm = so.seeking
if so.scope == 'words':
finalhitlines = paredowntowithinxwords(so, firstterm, secondterm,
maybefinalhitines)
else:
finalhitlines = maybefinalhitines
# to humor rewriteskgandprx()
# but that formatting doesn't 100% work yet...
so.termone = firstterm
so.termtwo = secondterm
so.lemmatwo = so.lemmaone
return finalhitlines