1.1 --- a/test.py Tue Feb 08 00:08:27 2011 +0100
1.2 +++ b/test.py Thu Feb 10 01:19:13 2011 +0100
1.3 @@ -52,14 +52,14 @@
1.4 f = open("testMS", "wb")
1.5 w = FileWriter(f)
1.6 w.begin_record()
1.7 -w.write_monotonic_sequence(tuples)
1.8 +w.write_monotonic_sequence(tuples, 2)
1.9 w.end_record()
1.10 w.close()
1.11
1.12 f = open("testMS", "rb")
1.13 r = FileReader(f)
1.14 r.begin_record()
1.15 -for t, t2 in zip(r.read_monotonic_sequence(), tuples):
1.16 +for t, t2 in zip(r.read_monotonic_sequence(2), tuples):
1.17 print t == t2, t, t2
1.18 r.end_record()
1.19 r.close()
1.20 @@ -69,14 +69,14 @@
1.21 f = open("testNMS", "wb")
1.22 w = FileWriter(f)
1.23 w.begin_record()
1.24 -w.write_delta_sequence(tuples2)
1.25 +w.write_delta_sequence(tuples2, 2)
1.26 w.end_record()
1.27 w.close()
1.28
1.29 f = open("testNMS", "rb")
1.30 r = FileReader(f)
1.31 r.begin_record()
1.32 -for t, t2 in zip(r.read_delta_sequence(), tuples2):
1.33 +for t, t2 in zip(r.read_delta_sequence(2), tuples2):
1.34 print t == t2, t, t2
1.35 r.end_record()
1.36 r.close()
1.37 @@ -99,20 +99,21 @@
1.38
1.39 f = open("testP", "wb")
1.40 w = PositionWriter(f)
1.41 +w.begin(0, 0)
1.42 for doc_positions in all_doc_positions:
1.43 + w.reset()
1.44 for docnum, positions in doc_positions:
1.45 w.write_positions(docnum, positions)
1.46 - w.reset()
1.47 w.close()
1.48
1.49 f = open("testP", "rb")
1.50 r = PositionReader(f)
1.51 for doc_positions in all_doc_positions:
1.52 + r.reset()
1.53 for docnum, positions in doc_positions:
1.54 d, p = r.read_positions()
1.55 print docnum == d, docnum, d
1.56 print positions == p, positions, p
1.57 - r.reset()
1.58 r.close()
1.59
1.60 all_doc_positions_seq = [
1.61 @@ -131,20 +132,21 @@
1.62
1.63 f = open("testP2", "wb")
1.64 w = PositionWriter(f)
1.65 +w.begin(2, 2)
1.66 for doc_positions in all_doc_positions_seq:
1.67 + w.reset()
1.68 for docnum, positions in doc_positions:
1.69 w.write_positions(docnum, positions)
1.70 - w.reset()
1.71 w.close()
1.72
1.73 f = open("testP2", "rb")
1.74 r = PositionReader(f)
1.75 for doc_positions in all_doc_positions_seq:
1.76 + r.reset()
1.77 for docnum, positions in doc_positions:
1.78 d, p = r.read_positions()
1.79 print docnum == d, docnum, d
1.80 print positions == p, positions, p
1.81 - r.reset()
1.82 r.close()
1.83
1.84 print "- Test position index files."
1.85 @@ -163,6 +165,7 @@
1.86 offsets = []
1.87 f = open("testPI", "wb")
1.88 w = PositionIndexWriter(f)
1.89 +w.begin(0)
1.90 for term_positions in indexed_positions:
1.91 offset = None
1.92 doc_frequency = 0
1.93 @@ -224,12 +227,15 @@
1.94
1.95 f = open("testF", "wb")
1.96 w = FieldWriter(f)
1.97 +w.begin(0)
1.98 +w.reset()
1.99 for docnum, fields in doc_fields:
1.100 w.write_fields(docnum, list(enumerate(fields)))
1.101 w.close()
1.102
1.103 f = open("testF", "rb")
1.104 r = FieldReader(f)
1.105 +r.reset()
1.106 for docnum, fields in doc_fields:
1.107 dn, df = r.read_fields()
1.108 print docnum == dn, docnum, dn
1.109 @@ -246,12 +252,15 @@
1.110
1.111 f = open("testFI", "wb")
1.112 w = FieldIndexWriter(f)
1.113 +w.begin(0)
1.114 +w.reset()
1.115 for docnum, offset in indexed_docs:
1.116 w.write_document(docnum, offset)
1.117 w.close()
1.118
1.119 f = open("testFI", "rb")
1.120 r = FieldIndexReader(f)
1.121 +r.reset()
1.122 for docnum, offset in indexed_docs:
1.123 dn, o = r.read_document()
1.124 print docnum == dn, docnum, dn
1.125 @@ -306,12 +315,14 @@
1.126
1.127 f = open("test", "wb")
1.128 w = TermWriter(f)
1.129 +w.reset()
1.130 for term, offset, frequency, doc_frequency in terms:
1.131 w.write_term(term, offset, frequency, doc_frequency)
1.132 w.close()
1.133
1.134 f = open("test", "rb")
1.135 r = TermReader(f)
1.136 +r.reset()
1.137 for term, offset, frequency, doc_frequency in terms:
1.138 t, o, fr, df = r.read_term()
1.139 print term == t, term, t
1.140 @@ -334,12 +345,14 @@
1.141
1.142 f = open("test", "wb")
1.143 w = TermIndexWriter(f)
1.144 +w.reset()
1.145 for term, offset, frequency, doc_frequency, info_offset in indexed_terms:
1.146 w.write_term(term, offset, frequency, doc_frequency, info_offset)
1.147 w.close()
1.148
1.149 f = open("test", "rb")
1.150 r = TermIndexReader(f)
1.151 +r.reset()
1.152 for term, offset, frequency, doc_frequency, info_offset in indexed_terms:
1.153 t, o, fr, df, i = r.read_term()
1.154 print term == t, term, t