3

Please login or register to vote for this query.

(click on this box to dismiss)

Lists the most commonly used tags with empty/missing/short tag wikis (wiki or excerpt). Can also identify tag wikis that are over a specified length. Enter -1 for all parameters to match all tags. Tags that have been synonymized are excluded.

Q&A about the site for the craft of professional writing, including fiction, non-fiction, technical, scholarly, and commercial writing

-- MaxBodyLength: Body shorter than "Set to 0 or -1 to disable"
DECLARE @max_body_len int = ##MaxBodyLength:int?0##
-- MaxExcerptLength: or excerpt shorter than "Set to 0 or -1 to disable"
DECLARE @max_excerpt_len int = ##MaxExcerptLength:int?1##
-- MinBodyLength: or body longer than "Set to -1 to disable"
DECLARE @min_body_len int = ##MinBodyLength:int?12000##
-- MinExcerptLength: or excerpt longer than "Set to -1 to disable"
DECLARE @min_excerpt_len int = ##MinExcerptLength:int?-1##
-- PlotMinimum: Plot: Start at "Must be a multiple of bin size"
DECLARE @plot_min int = ##PlotMinimum:int?0##
-- Bin: Plot: Bin size
DECLARE @bin int = ##Bin:Int?1##
-- BinCount: Plot: Number of bins "Maximum 999"
DECLARE @bin_count int = ##BinCount:int?20##

SELECT t.Count,
       t.TagName,
       coalesce(len(pe.Body),0) as [Excerpt length],
       coalesce(len(pw.Body),0) as [Wiki length],
       pe.CreationDate,
       -- Synonym target and ApprovalDate only exist for tag synonyms.
       tssrc.TargetTagName as [Synonym target],
       tssrc.ApprovalDate
INTO   #TagList
FROM   Tags t
       LEFT JOIN Posts pe on pe.Id = t.ExcerptPostId
       LEFT JOIN Posts pw on pw.Id = t.WikiPostId
       LEFT JOIN TagSynonyms tssrc on tssrc.SourceTagName = t.TagName
       LEFT JOIN Tags tgt on tssrc.TargetTagName = tgt.TagName
WHERE  -- match everything if all parameters are disabled
       (@max_body_len <= 0 and @max_excerpt_len <= 0
        and @min_body_len = -1 and @min_excerpt_len = -1)
       or (coalesce(len(pe.Body),0) < @max_excerpt_len -- short excerpt
        or coalesce(len(pw.Body),0) < @max_body_len    -- short wiki
        or len(pe.Body) > nullif(@min_excerpt_len,-1)  -- long excerpt
        or len(pw.Body) > nullif(@min_body_len,-1))    -- long wiki
        and (tssrc.SourceTagName is null   -- exclude tags that are synonyms
             or tssrc.ApprovalDate is null -- unless it was never approved
             or tgt.TagName is null)       -- or the synonym target is gone

-- Make a list of integers
-- Based on http://stackoverflow.com/questions/2157282/generate-days-from-date-range/2157776#2157776
select num
into #Integers
from
 (select @plot_min + (a.a + (10 * b.a) + (100 * c.a)) * @bin as num
  from (select 0 as a union all select 1 union all select 2 union all select 3 union all select 4 union all select 5 union all select 6 union all select 7 union all select 8 union all select 9) as a
    cross join (select 0 as a union all select 1 union all select 2 union all select 3 union all select 4 union all select 5 union all select 6 union all select 7 union all select 8 union all select 9) as b
    cross join (select 0 as a union all select 1 union all select 2 union all select 3 union all select 4 union all select 5 union all select 6 union all select 7 union all select 8 union all select 9) as c
 ) a
where a.num <= (select max(Count) from #TagList where Count <= (@plot_min + @bin*@bin_count))

SELECT *
FROM #TagList
ORDER BY Count desc,
    [Excerpt length] asc,
    [Wiki length] asc,
    TagName

SELECT num as [Number of questions],
       count(Count) as [Number of tags with this many questions]
FROM #TagList
--RIGHT JOIN #Integers on num=Count/@bin*@bin
RIGHT JOIN #Integers on Count between num and (num+@bin-1)
GROUP BY num
ORDER BY num

view current version

edited apr 24 16 amaranth

created feb 1 13 e