SQL/REGEX 谜题/挑战 如何将具有多个字符的 ASCII 艺术范围转换为关系数据？

Question

• 这里的动机是为nested ranges challenge 轻松准确地生成数据样本。

---

一个表包含一个文本类型的列。 文本包含一行或多行，其中每行包含一个或多个由字母创建的部分。 目标是编写一个查询，为每个部分返回一个元组及其起点、终点和值。

---

数据样本

create table t (txt varchar (1000));

insert into t (txt) values
(
'
AAAAAAAAAAAAAAAAAAAAAAAAAAAA  BBBB    CCCCCCCCCCCCCCCCCCCCCCCCC
DDDE  FFFFFFFF    GGGGGGGGG               HHHHHHHH    IIIIIII
JJ      KKKLLL       MM NN                              OOOOO
            P                                              QQ
'
)
;

---

要求的结果

* 只需要最后 3 列（部分 start/end/val），其余用于调试目的。

line_ind    section_ind   section_length  section_start  section_end   section_val
1           1             28              1              28            A
1           2             4               31             34            B
1           3             25              39             63            C
2           1             3               1              3             D
2           2             1               4              4             E
2           3             8               7              14            F
2           4             9               19             27            G
2           5             8               43             50            H
2           6             7               55             61            I
3           1             2               1              2             J
3           2             3               9              11            K
3           3             3               12             14            L
3           4             2               22             23            M
3           5             2               25             26            N
3           6             5               57             61            O
4           1             1               13             13            P
4           2             2               60             61            Q

Answer 1

Teradata

• 目前 regexp_split_to_table 似乎不支持零长度表达式（我创建了事件 RECGZJKZV）。为了克服这个限制，我使用 regexp_replace 来推动相邻字母序列之间的空间，例如KKKLLL

---

with        l
            as
            (
                select      line_ind
                           ,line

                from        table
                            (
                                regexp_split_to_table (-1,t.txt,'\r','')
                                returns (minus_one int,line_ind int,line varchar(1000))
                            )   
                            as l
            )

select      l.line_ind
           ,r.section_ind                                           
           ,char_length     (r.section)                                 as section_length
           ,regexp_instr    (l.line,'(\S)\1*',1,r.section_ind,0)        as section_start
           ,regexp_instr    (l.line,'(\S)\1*',1,r.section_ind,1) - 1    as section_end
           ,substr          (r.section,1,1)                             as section_val

from        table
            (
                regexp_split_to_table (l.line_ind,regexp_replace (l.line,'(?<=(?P<c>.))(?!(?P=c))',' '),'\s+','')
                returns (line_ind int,section_ind int,section varchar(1000))
            )  
            as r
           ,l

where       l.line_ind  =
            r.line_ind

order by    l.line_ind
           ,r.section_ind   
;

甲骨文

select      regexp_instr  (txt,'(\S)\1*',1,level,0)       - instr (txt,chr(10),regexp_instr (txt,'(\S)\1*',1,level,0) - length (txt) - 1,1)   as section_start
           ,regexp_instr  (txt,'(\S)\1*',1,level,1) - 1   - instr (txt,chr(10),regexp_instr (txt,'(\S)\1*',1,level,0) - length (txt) - 1,1)   as section_end
           ,regexp_substr (txt,'(\S)\1*',1,level,'',1)                                                                                        as section_val

from        t

connect by  level <= regexp_count (txt,'(\S)\1*')
;

Answer 2

甲骨文

即使您有多个输入行，这也会起作用：

WITH lines ( txt, id, line, pos, line_no ) AS(
  SELECT txt,
         id,
         REGEXP_SUBSTR( txt, '.*', 1, 1 ),
         REGEXP_INSTR( txt, '.*', 1, 1, 1 ),
         1
  FROM   t
UNION ALL
  SELECT txt,
         id,
         REGEXP_SUBSTR( txt, '.*', pos + 1, 1 ),
         REGEXP_INSTR( txt, '.*', pos + 1, 1, 1 ),
         line_no + 1
  FROM   lines
  WHERE  pos > 0
),
words ( id, line, line_no, section_start, section_end, section_value ) AS (
  SELECT id,
         line,
         line_no,
         REGEXP_INSTR( line, '(\S)\1*', 1, 1, 0 ),
         REGEXP_INSTR( line, '(\S)\1*', 1, 1, 1 ) - 1,
         REGEXP_SUBSTR( line, '(\S)\1*', 1, 1, NULL, 1 )
  FROM   lines
  WHERE  pos > 0
  AND    line IS NOT NULL
UNION ALL
  SELECT id,
         line,
         line_no,
         REGEXP_INSTR( line, '(\S)\1*', section_end + 1, 1, 0 ),
         REGEXP_INSTR( line, '(\S)\1*', section_end + 1, 1, 1 ) - 1,
         REGEXP_SUBSTR( line, '(\S)\1*', section_end + 1, 1, NULL, 1 )
  FROM   words
  WHERE  section_end > 0
)
SELECT id,
       line_no,
       section_start,
       section_end,
       section_value
FROM   words
WHERE  section_end > 0
ORDER BY id, line_no, section_start

因此，对于输入数据（添加了id 列以便能够轻松区分文本片段）：

create table t (id NUMBER(5,0), txt varchar (1000));

insert into t (id, txt) values
(
1,
'
AAAAAAAAAAAAAAAAAAAAAAAAAAAA  BBBB    CCCCCCCCCCCCCCCCCCCCCCCCC
DDDE  FFFFFFFF    GGGGGGGGG               HHHHHHHH    IIIIIII
JJ      KKKLLL       MM NN                              OOOOO
            P                                              QQ
'
);

insert into t (id, txt) values ( 2, 'RRRSTT UUU    V WXYZ' );

这个输出：

身份证 | LINE_NO | SECTION_START | SECTION_END | SECTION_VALUE -: | ------: | ------------: | ----------: | :------------ 1 | 2 | 1 | 28 |一种 1 | 2 | 31 | 34 |乙 1 | 2 | 39 | 63 | C 1 | 3 | 1 | 3 | D 1 | 3 | 4 | 4 |乙 1 | 3 | 7 | 14 | F 1 | 3 | 19 | 27 | G 1 | 3 | 43 | 50 | H 1 | 3 | 55 | 61 |一世 1 | 4 | 1 | 2 | Ĵ 1 | 4 | 9 | 11 | ķ 1 | 4 | 12 | 14 |大号 1 | 4 | 22 | 23 |米 1 | 4 | 25 | 26 | ñ 1 | 4 | 57 | 61 | ○ 1 | 5 | 13 | 13 |磷 1 | 5 | 60 | 61 |问 2 | 1 | 1 | 3 | R 2 | 1 | 4 | 4 |小号 2 | 1 | 5 | 6 |吨 2 | 1 | 8 | 10 | ü 2 | 1 | 15 | 15 |五 2 | 1 | 17 | 17 | W 2 | 1 | 18 | 18 | X 2 | 1 | 19 | 19 |是 2 | 1 | 20 | 20 | Z

db小提琴here