问题描述
我在表中有一个字符串clob值,我需要将其分成几列。 源表查询:
JavascriptExecutor js = (JavascriptExecutor) driver;
js.executeScript("document.getElementById('Div_Id').innerHTML="+ DesiredText);
在clob列的值中也有空格,空值和行间距。 因此,当我尝试使用
进行拆分时Insert into disp_data(id,data) values(100,'"Project title as per the outstanding Requirements","The values are not with respect to the requirement and analysis done by the team.
Also it is difficult to prepare a scenario notwithstanding the fact it is difficult. This user story is going to be slightly complex however it is up to the team","Active","disabled","25 tonnes of fuel","www.examplesites.com/html.asp&net;","","25"');
问题是针对带有行距的大文本,它将文本分成不同的行。我曾考虑过使用上面的结果集和数据透视表,但无法。
我需要将此数据作为列获取,并推入目标表-push_data_temp。
select regexp_substr(data,'[^,]+',1,level) from disp_data
connect by regexp_substr(data,level) is not null.
clob列具有11个逗号分隔的值,需要将它们作为列推入该表。 这整个过程需要通过pl / sql过程完成。
非常感谢您的帮助。 DB是oracle 19c
解决方法
您的正则表达式needs to allow for nulls,即连续的逗号(但希望您在任何引用的字符串中都没有逗号...)。如果您有多个源行,那么使用递归CTE进行拆分会更容易:
with rcte (id,data,lvl,result) as (
select id,1,regexp_substr(data,'(.*?)(,|$)',null,1)
from disp_data
union all
select id,lvl + 1,1)
from rcte
where lvl <= regexp_count(data,',')
)
select id,result
from rcte
order by id,lvl;
然后您可以将结果旋转到所需的列:
with rcte (id,')
)
select *
from (
select id,result
from rcte
)
pivot (max(result) as col for (lvl) in (1,2,3,4,5,6,7,8,9,10,11));
您可以直接在插入语句中使用它:
insert into push_data_temp (pid,col1,col2,col3,col4,col5,col6,col7,col8,col9,col10,col11)
with rcte (id,11));
不需要PL / SQL,但是如果需要,您仍然可以将其包装在过程中。
我必须把它当作clob,并且由于数据类型不一致而引发错误
您需要将令牌强制转换为varchar2
,从而限制了令牌的长度(根据Oracle版本和设置,限制为4k或32k):
with rcte (id,cast(regexp_substr(data,1) as varchar2(4000))
from disp_data
union all
select id,1) as varchar2(4000))
from rcte
where lvl <= regexp_count(data,')
)
...
db<>fiddle,带有CLOB(并删除了连接示例,因为它们破坏了它...)
当我尝试使用逗号之间的文本时,它会不均匀地拆分数据。
这就是为什么我说“希望您在任何引用的字符串中都没有逗号”。由于您没有任何真正为空的元素-您拥有...","","...
而不是...,...
-您可以跳过对我想的那些元素的关注,并使用其他模式:
with rcte (id,'("[^"]*"|[^,]+)',]+)')
)
...
如果确实必须处理空元素,那么but more work仍然是可能的。这也不会处理没有字符串的转义双引号。在某些时候,用PL / SQL编写自己的解析器会更容易。甚至将数据写到磁盘上并作为外部表读回,可以为您处理所有这些事情。
,输入Polymorphic Table Functions!
您可以使用它们来动态转换comma-separated strings into a list of columns:
create table disp_data (
id int,data varchar2(1000)
);
Insert into disp_data(id,data) values(100,'"Project title as per the outstanding Requirements","The values are not with respect to the requirement and analysis done by the team.
Also it is difficult to prepare a scenario notwithstanding the fact it is difficult. This user story is going to be slightly complex however it is up to the team","Active","Disabled","25 tonnes of fuel","www.examplesites.com/html.asp&net;","25"');
commit;
create or replace package csv_pkg as
/* The describe function defines the new columns */
function describe (
tab in out dbms_tf.table_t,col_names varchar2
) return dbms_tf.describe_t;
/* Fetch_rows sets the values for the new columns */
procedure fetch_rows (col_names varchar2);
end csv_pkg;
/
create or replace package body csv_pkg as
function describe(
tab in out dbms_tf.table_t,col_names varchar2
)
return dbms_tf.describe_t as
new_cols dbms_tf.columns_new_t;
col_id pls_integer := 2;
begin
/* Enable the source colun for reading */
tab.column(1).pass_through := FALSE;
tab.column(1).for_read := TRUE;
new_cols(1) := tab.column(1).description;
/* Extract the column names from the header string,creating a new column for each
*/
for j in 1 .. ( length(col_names) - length(replace(col_names,')) ) + 1 loop
new_cols(col_id) := dbms_tf.column_metadata_t(
name=>regexp_substr(col_names,'[^,]+',j),--'c'||j,type=>dbms_tf.type_varchar2
);
col_id := col_id + 1;
end loop;
return dbms_tf.describe_t( new_columns => new_cols );
end;
procedure fetch_rows (col_names varchar2) as
rowset dbms_tf.row_set_t;
row_count pls_integer;
begin
/* read the input data set */
dbms_tf.get_row_set(rowset,row_count => row_count);
/* Loop through the input rows... */
for i in 1 .. row_count loop
/* ...and the defined columns,extracting the relevant value
start from 2 to skip the input string
*/
for j in 2 .. ( length(col_names) - length(replace(col_names,')) ) + 2 loop
rowset(j).tab_varchar2(i) :=
regexp_substr(rowset(1).tab_varchar2(i),j - 1);
end loop;
end loop;
/* Output the new columns and their values */
dbms_tf.put_row_set(rowset);
end;
end csv_pkg;
/
create or replace function csv_to_columns(
tab table,col_names varchar2
) return table pipelined row polymorphic using csv_pkg;
/
with rws as (
select data from disp_data
)
select c1,c2,c4,c5,c6,c11
from csv_to_columns (
rws,'c1,c3,c7,c8,c9,c10,c11'
);
C1 C2 C4 C4 C5 C6 C11
-------------------- ------------------------------ ---------- ---------- ---------- -------------------- ----------
"Project title as pe "The values are not with respe "Disabled" "Disabled" "25 tonnes "www.examplesites.co "25"
r the outstanding Re ct to the requirement and anal of fuel" m/html.asp&net;"
quirements" ysis done by the team.
Also it is difficult to prepar
e a scenario notwithstanding t
he fact it is difficult. This
user story is going to be slig
htly complex however it is up
to the team"