aboutsummaryrefslogtreecommitdiffstats
path: root/searchlib/src/vespa/searchlib/index/schemautil.cpp
blob: 98574f8485b830d0f090ab8b50abbfbb68cf3fb1 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
// Copyright Vespa.ai. Licensed under the terms of the Apache 2.0 license. See LICENSE in the project root.

#include "schemautil.h"
#include <set>
#include <fstream>
#include <cassert>

#include <vespa/log/log.h>
LOG_SETUP(".index.schemautil");

namespace search::index {

using schema::DataType;

SchemaUtil::IndexSettings
SchemaUtil::getIndexSettings(const Schema &schema,
                             const uint32_t index)
{
    Schema::DataType indexDataType(DataType::STRING);
    bool error = false;

    const Schema::IndexField &iField = schema.getIndexField(index);
    indexDataType = iField.getDataType();
    if (indexDataType != DataType::STRING) {
        error = true;
        LOG(error, "Field %s has bad data type", iField.getName().c_str());
    }

    return IndexSettings(indexDataType, error);
}

bool
SchemaUtil::IndexIterator::hasOldFields(const Schema &oldSchema) const
{
    assert(isValid());
    const Schema::IndexField &newField =
        getSchema().getIndexField(getIndex());
    const vespalib::string &fieldName = newField.getName();
    uint32_t oldFieldId = oldSchema.getIndexFieldId(fieldName);
    if (oldFieldId == Schema::UNKNOWN_FIELD_ID) {
        return false;
    }
    const Schema::IndexField &oldField =
        oldSchema.getIndexField(oldFieldId);
    if (oldField.getDataType() != newField.getDataType()) {
        return false;   // wrong data type
    }
    return true;
}

bool
SchemaUtil::IndexIterator::hasMatchingOldFields(const Schema &oldSchema) const
{
    assert(isValid());
    const Schema::IndexField &newField =
        getSchema().getIndexField(getIndex());
    const vespalib::string &fieldName = newField.getName();
    uint32_t oldFieldId = oldSchema.getIndexFieldId(fieldName);
    if (oldFieldId == Schema::UNKNOWN_FIELD_ID) {
        return false;
    }
    const Schema::IndexField &oldField =
        oldSchema.getIndexField(oldFieldId);
    if (oldField.getDataType() != newField.getDataType() ||
        oldField.getCollectionType() != newField.getCollectionType())
    {
        return false;
    }
    return true;
}

bool
SchemaUtil::IndexIterator::has_matching_use_interleaved_features(const Schema &oldSchema) const
{
    assert(isValid());
    const Schema::IndexField &newField = getSchema().getIndexField(getIndex());
    const vespalib::string &fieldName = newField.getName();
    uint32_t oldFieldId = oldSchema.getIndexFieldId(fieldName);
    if (oldFieldId == Schema::UNKNOWN_FIELD_ID) {
        return false;
    }
    const Schema::IndexField &oldField = oldSchema.getIndexField(oldFieldId);
    return (oldField.use_interleaved_features() == newField.use_interleaved_features());
}

bool
SchemaUtil::validateIndexField(const Schema::IndexField &field)
{
    bool ok = true;
    if (!validateIndexFieldType(field.getDataType())) {
        LOG(error,
            "Field %s has bad data type",
            field.getName().c_str());
        ok = false;
    }
    return ok;
}

bool
SchemaUtil::addIndexField(Schema &schema,
                          const Schema::IndexField &field)
{
    bool ok = true;
    if (!validateIndexField(field)) {
        ok = false;
    }
    uint32_t fieldId = schema.getIndexFieldId(field.getName());
    if (fieldId != Schema::UNKNOWN_FIELD_ID) {
        LOG(error,
            "Field %s already exists in schema",
            field.getName().c_str());
        ok = false;
    }
    if (ok) {
        schema.addIndexField(field);
    }
    return ok;
}

bool
SchemaUtil::validateSchema(const Schema &schema)
{
    bool ok = true;
    for (IndexIterator it(schema); it.isValid(); ++it) {
        uint32_t fieldId = it.getIndex();
        const Schema::IndexField &field = schema.getIndexField(fieldId);
        if (!validateIndexField(field)) {
            ok = false;
        }
        if (schema.getIndexFieldId(field.getName()) != fieldId) {
            LOG(error,
                "Duplcate field %s",
                field.getName().c_str());
            ok = false;
        }
    }
    for (uint32_t fsId = 0; fsId < schema.getNumFieldSets(); ++fsId) {
        const Schema::FieldSet &fs = schema.getFieldSet(fsId);
        if (schema.getFieldSetId(fs.getName()) != fsId) {
            LOG(error,
                "Duplicate field set %s",
                fs.getName().c_str());
            ok = false;
        }
    }
    return ok;
}

bool
SchemaUtil::getIndexIds(const Schema &schema,
                        schema::DataType dataType,
                        std::vector<uint32_t> &indexes)
{
    indexes.clear();
    for (IndexIterator i(schema); i.isValid(); ++i) {
        SchemaUtil::IndexSettings settings = i.getIndexSettings();
        if (settings.hasError()) {
            return false;
        }
        if (settings.getDataType() == dataType) {
            indexes.push_back(i.getIndex());
        }
    }
    return true;
}

}