jest to możliwe tylko w czystym MySQL bez użycia pełnego parsera HTML lub UDF, który zaimportowałby funkcję REGEX_REPLACE do MySQL.
Sztuczka polega na użyciu generatora liczb i użyciu zagnieżdżonego SUBSTRING_INDEX do podzielenia dużego ciągu na znaczniki html
Ten generator liczb wygeneruje liczbę od 1 do 10.000
Więc "parser" będzie obsługiwać do 10 000 tagów, jeśli potrzebujesz więcej, musisz dodać więcej
CROSS JOIN (
SELECT 1 UNION SELECT 2 UNION SELECT 3 UNION SELECT 4 UNION SELECT 5 UNION SELECT 6 UNION SELECT 7 UNION SELECT 8 UNION SELECT 9 UNION SELECT 10
) AS record_[number]
Zapytanie
SELECT
(@number := @number + 1) AS number
FROM (
SELECT 1 UNION SELECT 2 UNION SELECT 3 UNION SELECT 4 UNION SELECT 5 UNION SELECT 6 UNION SELECT 7 UNION SELECT 8 UNION SELECT 9 UNION SELECT 10
) AS record_1
CROSS JOIN (
SELECT 1 UNION SELECT 2 UNION SELECT 3 UNION SELECT 4 UNION SELECT 5 UNION SELECT 6 UNION SELECT 7 UNION SELECT 8 UNION SELECT 9 UNION SELECT 10
) AS record_2
CROSS JOIN (
SELECT 1 UNION SELECT 2 UNION SELECT 3 UNION SELECT 4 UNION SELECT 5 UNION SELECT 6 UNION SELECT 7 UNION SELECT 8 UNION SELECT 9 UNION SELECT 10
) AS record_3
CROSS JOIN (
SELECT 1 UNION SELECT 2 UNION SELECT 3 UNION SELECT 4 UNION SELECT 5 UNION SELECT 6 UNION SELECT 7 UNION SELECT 8 UNION SELECT 9 UNION SELECT 10
) AS record_4
CROSS JOIN ( SELECT @number := 0 ) AS init_user_param
ta instrukcja SQL zostanie użyta do podziału na tagu HTML
Oświadczenie SQL
CONCAT(SUBSTRING_INDEX(SUBSTRING_INDEX([large_html_string], ">", [tag_position]), ">", -1), ">") as tag
Sztuczka polega teraz na połączeniu generatora liczb i podziału ciągu html. Zatem [tag_position] jest wypełniana liczbą z generatora liczb.
Odbywa się to za pomocą CROSS JOIN.
Zapytanie
SELECT
*
FROM (
SELECT
CONCAT(SUBSTRING_INDEX(SUBSTRING_INDEX(data, ">", generator.number), ">", -1), ">") as tag
FROM (
SELECT '<p><span><b>C10373 - FIAT GROUP AUTOMOBILES/RAMO DI AZIENDA DI KUEHNE + NAGEL</b></span>
<p>la somma pari a € 400+IVA per l’attività</p>
<p>TELE+ A 20.000 LIRE AL MESE </p>
<li>a mano o via fax al numero +39.00.0.0.0.00.</li>
<p>Il punteggio base sarà incrementato di un <strong>+ </strong>al ricorrere di ciascuna delle seguenti condizioni:</p>
<li><a href="/aaa/gare/CIGZB81E5568D+RDO1560277+Obblighi+contattuali-signed.pdf" title="">Obblighi contrattuali</a></li>
<li><a href="/aaa/gare/CIGZB81E5568D+RDO1560277+Obblighi+contattuali-signed.pdf" title="">Obblighi contrattuali</a></li>
<li><a href="/aaa/gare/CIGZB81E5568D+RDO_1560277Lettera_Invito.pdf" title="">Lettera di invito</a></li>
<li><a href="/aaa/gare/CIGZB81E5568D+RDO1560277+Obblighi+contattuali-signed.pdf" title="">Obblighi contrattuali</a></li>
<li><a href="/aaa/gare/CIGZB81E5568D+RDO1560277+disciplinare+di+gara-signed.pdf" title="">Disciplinare di gara</a></li>
<li><a href="/aaa/gare/CIGZB81E5568D+determina+di+aggiudicazione+58+2017.pdf" title="">Determina di aggiudicazione</a></li>' AS data
) AS record
CROSS JOIN (
SELECT
(@number := @number + 1) AS number
FROM (
SELECT 1 UNION SELECT 2 UNION SELECT 3 UNION SELECT 4 UNION SELECT 5 UNION SELECT 6 UNION SELECT 7 UNION SELECT 8 UNION SELECT 9 UNION SELECT 10
) AS record_1
CROSS JOIN (
SELECT 1 UNION SELECT 2 UNION SELECT 3 UNION SELECT 4 UNION SELECT 5 UNION SELECT 6 UNION SELECT 7 UNION SELECT 8 UNION SELECT 9 UNION SELECT 10
) AS record_2
CROSS JOIN (
SELECT 1 UNION SELECT 2 UNION SELECT 3 UNION SELECT 4 UNION SELECT 5 UNION SELECT 6 UNION SELECT 7 UNION SELECT 8 UNION SELECT 9 UNION SELECT 10
) AS record_3
CROSS JOIN (
SELECT 1 UNION SELECT 2 UNION SELECT 3 UNION SELECT 4 UNION SELECT 5 UNION SELECT 6 UNION SELECT 7 UNION SELECT 8 UNION SELECT 9 UNION SELECT 10
) AS record_4
CROSS JOIN ( SELECT @number := 0 ) AS init_user_param
)
AS generator
)
AS tags
WHERE
tags.tag != '>'
zobacz demo http://www.sqlfiddle.com/#!9/de2ed/32
Teraz mamy tagi jako oddzielne rekordy, które naprawdę łatwo zastąpić tylko w rekordach, które zawierają „href”.
Instrukcja SQL
(
CASE
WHEN
LOCATE("href", tags.tag) > 0
THEN
REPLACE(tags.tag, "+", " ")
ELSE
tags.tag
END
) AS tag
zobacz demo http://www.sqlfiddle.com/#!9/de2ed/38
Teraz, gdy wiemy, jak zastąpić, teraz scalimy rekordy z powrotem w jeden ciąg. Możemy do tego użyć GROUP_CONCAT.
Zapytanie
SET SESSION group_concat_max_len = @@max_allowed_packet;
SELECT
GROUP_CONCAT(
CASE
WHEN
LOCATE("href", tags.tag) > 0
THEN
REPLACE(tags.tag, "+", " ")
ELSE
tags.tag
END
SEPARATOR ""
) AS html
FROM (
SELECT
CONCAT(SUBSTRING_INDEX(SUBSTRING_INDEX(data, ">", generator.number), ">", -1), ">") as tag
FROM (
SELECT '<p><span><b>C10373 - FIAT GROUP AUTOMOBILES/RAMO DI AZIENDA DI KUEHNE + NAGEL</b></span>
<p>la somma pari a € 400+IVA per l’attività</p>
<p>TELE+ A 20.000 LIRE AL MESE </p>
<li>a mano o via fax al numero +39.00.0.0.0.00.</li>
<p>Il punteggio base sarà incrementato di un <strong>+ </strong>al ricorrere di ciascuna delle seguenti condizioni:</p>
<li><a href="/aaa/gare/CIGZB81E5568D+RDO1560277+Obblighi+contattuali-signed.pdf" title="">Obblighi contrattuali</a></li>
<li><a href="/aaa/gare/CIGZB81E5568D+RDO1560277+Obblighi+contattuali-signed.pdf" title="">Obblighi contrattuali</a></li>
<li><a href="/aaa/gare/CIGZB81E5568D+RDO_1560277Lettera_Invito.pdf" title="">Lettera di invito</a></li>
<li><a href="/aaa/gare/CIGZB81E5568D+RDO1560277+Obblighi+contattuali-signed.pdf" title="">Obblighi contrattuali</a></li>
<li><a href="/aaa/gare/CIGZB81E5568D+RDO1560277+disciplinare+di+gara-signed.pdf" title="">Disciplinare di gara</a></li>
<li><a href="/aaa/gare/CIGZB81E5568D+determina+di+aggiudicazione+58+2017.pdf" title="">Determina di aggiudicazione</a></li>' AS data
) AS record
CROSS JOIN (
SELECT
(@number := @number + 1) AS number
FROM (
SELECT 1 UNION SELECT 2 UNION SELECT 3 UNION SELECT 4 UNION SELECT 5 UNION SELECT 6 UNION SELECT 7 UNION SELECT 8 UNION SELECT 9 UNION SELECT 10
) AS record_1
CROSS JOIN (
SELECT 1 UNION SELECT 2 UNION SELECT 3 UNION SELECT 4 UNION SELECT 5 UNION SELECT 6 UNION SELECT 7 UNION SELECT 8 UNION SELECT 9 UNION SELECT 10
) AS record_2
CROSS JOIN (
SELECT 1 UNION SELECT 2 UNION SELECT 3 UNION SELECT 4 UNION SELECT 5 UNION SELECT 6 UNION SELECT 7 UNION SELECT 8 UNION SELECT 9 UNION SELECT 10
) AS record_3
CROSS JOIN (
SELECT 1 UNION SELECT 2 UNION SELECT 3 UNION SELECT 4 UNION SELECT 5 UNION SELECT 6 UNION SELECT 7 UNION SELECT 8 UNION SELECT 9 UNION SELECT 10
) AS record_4
CROSS JOIN ( SELECT @number := 0 ) AS init_user_param
)
AS generator
)
AS tags
WHERE
tags.tag != '>'
zobacz demo, aby zobaczyć pełne zapytanie
http://www.sqlfiddle.com/#!9/de2ed/46