pgsql: Doc: improve description of window function processing.

2025-03-13 Thread Tom Lane
Doc: improve description of window function processing. The previous wording talked about a "single pass over the data", which can be read as promising more than intended (to wit, that only one WindowAgg plan node will be used). What we promise is only what the SQL spec requires, namely that the

pgsql: Doc: improve description of window function processing.

2025-03-11 Thread Tom Lane
Doc: improve description of window function processing. The previous wording talked about a "single pass over the data", which can be read as promising more than intended (to wit, that only one WindowAgg plan node will be used). What we promise is only what the SQL spec requires, namely that the

pgsql: Doc: improve description of window function processing.

2025-03-11 Thread Tom Lane
Doc: improve description of window function processing. The previous wording talked about a "single pass over the data", which can be read as promising more than intended (to wit, that only one WindowAgg plan node will be used). What we promise is only what the SQL spec requires, namely that the

pgsql: Doc: improve description of window function processing.

2025-03-11 Thread Tom Lane
Doc: improve description of window function processing. The previous wording talked about a "single pass over the data", which can be read as promising more than intended (to wit, that only one WindowAgg plan node will be used). What we promise is only what the SQL spec requires, namely that the

pgsql: Doc: improve description of window function processing.

2025-03-10 Thread Tom Lane
Doc: improve description of window function processing. The previous wording talked about a "single pass over the data", which can be read as promising more than intended (to wit, that only one WindowAgg plan node will be used). What we promise is only what the SQL spec requires, namely that the

pgsql: Doc: improve description of window function processing.

2025-03-10 Thread Tom Lane
Doc: improve description of window function processing. The previous wording talked about a "single pass over the data", which can be read as promising more than intended (to wit, that only one WindowAgg plan node will be used). What we promise is only what the SQL spec requires, namely that the