Улучшение форматирования / распознавания текста с Solr

Мне интересно, есть ли способ очистить форматирование результатов, предоставляемых Solr (в частности, текстовое поле). Многие документы хорошо индексируются, и, когда их просят выделить, в большинстве случаев Solr возвращает довольно четкие результаты. К сожалению, есть немало незначительных результатов, которые, как представляется, состоят из текста / основных моментов очень низкого качества.

Я приложил 3 изображения. Все они взяты из одного документа. Не обращая внимания на черные полосы, мне пришлось редактировать некоторую конфиденциальную информацию перед публикацией. Во-первых, как PDF выглядит нормально. Второй иллюстрирует проблему с основными моментами, возвращаемыми, когда Solr запрашивается об этом документе. Третье изображение из основного текстового поля, а также показывает весь разжеванный текст. Вот как это выглядит в сыром XML.

Можно ли что-либо сделать, как во время индексации, так и во время запросов, чтобы улучшить распознавание или форматирование текста?

Как и было запрошено, вот соответствующие биты schema.xml:

<fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
<fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
<fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
<fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>

<fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
<fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>

<fieldType name="pint" class="solr.IntField"/>
<fieldType name="plong" class="solr.LongField"/>
<fieldType name="pfloat" class="solr.FloatField"/>
<fieldType name="pdouble" class="solr.DoubleField"/>
<fieldType name="pdate" class="solr.DateField" sortMissingLast="true"/>

<fieldType name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="slong" class="solr.SortableLongField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="sfloat" class="solr.SortableFloatField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true" omitNorms="true"/>

<fieldType name="random" class="solr.RandomSortField" indexed="true" />

<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
</analyzer>
</fieldType>

<fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>

<fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory"ignoreCase="true"words="lang/stopwords_en.txt"enablePositionIncrements="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPossessiveFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory"ignoreCase="true"words="lang/stopwords_en.txt"enablePositionIncrements="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPossessiveFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
</fieldType>

<fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory"ignoreCase="true"words="lang/stopwords_en.txt"enablePositionIncrements="true"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory"ignoreCase="true"words="lang/stopwords_en.txt"enablePositionIncrements="true"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
</fieldType>

<fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.EnglishMinimalStemFilterFactory"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>

<fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>

<fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
<analyzer>
<tokenizer class="solr.KeywordTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory" />
<filter class="solr.TrimFilterFactory" />
<filter class="solr.PatternReplaceFilterFactory"pattern="([^a-z])" replacement="" replace="all"/>
</analyzer>
</fieldType>

<fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
</analyzer>
</fieldtype>

<fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" >
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
</analyzer>
</fieldtype>

<fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.KeywordTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory" />
</analyzer>
</fieldType>

<fieldType name="text_path" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.PathHierarchyTokenizerFactory"/>
</analyzer>
</fieldType>

<fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />

<fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>

<fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>

<fieldtype name="geohash" class="solr.GeoHashField"/>

<fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />

<field name="weight" type="float" indexed="true" stored="true"/>
<field name="price"  type="float" indexed="true" stored="true"/>
<field name="popularity" type="int" indexed="true" stored="true" />
<field name="inStock" type="boolean" indexed="true" stored="true" />

<field name="store" type="location" indexed="true" stored="true"/>
<field name="title" type="text_general" indexed="true" stored="true" multiValued="true"/>
<field name="subject" type="text_general" indexed="true" stored="true"/>
<field name="description" type="text_general" indexed="true" stored="true"/>
<field name="comments" type="text_general" indexed="true" stored="true"/>
<field name="author" type="text_general" indexed="true" stored="true"/>
<field name="keywords" type="text_general" indexed="true" stored="true"/>
<field name="category" type="text_general" indexed="true" stored="true"/>
<field name="content_type" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="last_modified" type="date" indexed="true" stored="true"/>
<field name="links" type="string" indexed="true" stored="true" multiValued="true"/>

<field name="content" type="text_general" indexed="false" stored="true" multiValued="false"/>
<field name="text" type="text_general" indexed="true" stored="true" multiValued="true"/>

<field name="text_rev" type="text_general_rev" indexed="true" stored="false" multiValued="true"/>

<field name="manu_exact" type="string" indexed="true" stored="false"/>

<field name="payloads" type="payloads" indexed="true" stored="true"/>

<dynamicField name="*_i"  type="int"    indexed="true"  stored="true"/>
<dynamicField name="*_s"  type="string"  indexed="true"  stored="true"/>
<dynamicField name="*_l"  type="long"   indexed="true"  stored="true"/>
<dynamicField name="*_t"  type="text_general"    indexed="true"  stored="true"/>
<dynamicField name="*_txt" type="text_general"    indexed="true"  stored="true" multiValued="true"/>
<dynamicField name="*_en"  type="text_en"    indexed="true"  stored="true" multiValued="true" />
<dynamicField name="*_b"  type="boolean" indexed="true"  stored="true"/>
<dynamicField name="*_f"  type="float"  indexed="true"  stored="true"/>
<dynamicField name="*_d"  type="double" indexed="true"  stored="true"/>

<dynamicField name="*_coordinate"  type="tdouble" indexed="true"  stored="false"/>

<dynamicField name="*_dt" type="date"    indexed="true"  stored="true"/>
<dynamicField name="*_p"  type="location" indexed="true" stored="true"/>

<dynamicField name="*_ti" type="tint"    indexed="true"  stored="true"/>
<dynamicField name="*_tl" type="tlong"   indexed="true"  stored="true"/>
<dynamicField name="*_tf" type="tfloat"  indexed="true"  stored="true"/>
<dynamicField name="*_td" type="tdouble" indexed="true"  stored="true"/>
<dynamicField name="*_tdt" type="tdate"  indexed="true"  stored="true"/>

<dynamicField name="*_pi"  type="pint"    indexed="true"  stored="true"/>
<dynamicField name="*_c"   type="currency" indexed="true"  stored="true"/>

<dynamicField name="ignored_*" type="ignored" multiValued="true"/>
<dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>

<dynamicField name="random_*" type="random" />

<uniqueKey>id</uniqueKey>

<copyField source="cat" dest="text"/>
<copyField source="name" dest="text"/>
<copyField source="manu" dest="text"/>
<copyField source="features" dest="text"/>
<copyField source="includes" dest="text"/>
<copyField source="manu" dest="manu_exact"/>

<copyField source="price" dest="price_c"/>

Любая помощь будет отличной!