使用 glue_sql 进行 R SQL 模板化，能够动态删除 where 子句

Question

TLDR
我希望能够模板化 SQL 查询并在 R 中运行它们。胶水包和 DBI 工作得很好，但我想不出一种模板语句的方法。换句话说，有没有办法做这样的事情(借用 jinja ):

SELECT * FROM mtcars 
{% if length( {make} ) > 0 %} 
WHERE make IN( {make*}
{% end %}

其他详细信息
DBI 和胶水非常适合单个用例，但我经常想重用相同的通用 SQL 代码和 WHERE 子句等的一些不同变体。通常我希望 WHERE 处于“关闭”状态。在某些用例中而不是在其他用例中(例如对于 WHERE IN() 它默认为所有值，对于 WHERE x >= y 它不应用条件等等)。

我能找到的唯一解决方案是将 R 中的输入计算为 discussed here ，然后传递默认向量或输入。这种方法在某些用例中有效，而在其他用例中则完全无效。我认为这使得泛化变得更加困难并且在我最常见的用例中会影响性能 - 当我想要一个带有将值传递给 WHERE IN() 子句但默认为所有参数的查询时值。如果表在发展(即所有值随时间变化)，那么我需要先运行查询以获取所有值，然后在用户未提供值时输入它们。这在更大的 table 上可能会很昂贵，而且如果它在用户体验中( Shiny )则令人望而却步。

library(DBI)
library(glue)
library(dplyr, warn.conflicts =  F)

# Setup local DB #### 
con <- DBI::dbConnect(RSQLite::SQLite(), ":memory:")
mtcars_df <- tibble::rownames_to_column(mtcars, var = "make")
str(mtcars_df)
#> 'data.frame':    32 obs. of  12 variables:
#>  $ make: chr  "Mazda RX4" "Mazda RX4 Wag" "Datsun 710" "Hornet 4 Drive" ...
#>  $ mpg : num  21 21 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 ...
#>  $ cyl : num  6 6 4 6 8 6 8 4 4 6 ...
#>  $ disp: num  160 160 108 258 360 ...
#>  $ hp  : num  110 110 93 110 175 105 245 62 95 123 ...
#>  $ drat: num  3.9 3.9 3.85 3.08 3.15 2.76 3.21 3.69 3.92 3.92 ...
#>  $ wt  : num  2.62 2.88 2.32 3.21 3.44 ...
#>  $ qsec: num  16.5 17 18.6 19.4 17 ...
#>  $ vs  : num  0 0 1 1 0 1 0 1 1 1 ...
#>  $ am  : num  1 1 1 0 0 0 0 0 0 0 ...
#>  $ gear: num  4 4 4 3 3 3 3 4 4 4 ...
#>  $ carb: num  4 4 1 1 2 1 4 2 2 4 ...
DBI::dbWriteTable(con, "mtcars", mtcars_df)

# Example query ####
sql <- glue::glue_sql("SELECT * FROM mtcars WHERE make IN( {make*} )", make = c("Fiat X1-9", "Datsun 710"), .con = con)
DBI::dbGetQuery(con, sql) 
#>         make  mpg cyl disp hp drat    wt  qsec vs am gear carb
#> 1 Datsun 710 22.8   4  108 93 3.85 2.320 18.61  1  1    4    1
#> 2  Fiat X1-9 27.3   4   79 66 4.08 1.935 18.90  1  1    4    1

# Templating #### 
sql <- "SELECT * FROM mtcars WHERE make IN( {make*} )"
sql_template <- tempfile(fileext = ".sql")
readr::write_file(sql, sql_template)
read_sql <- function(file, ..., .con, .envir = parent.frame()){
  sql <- readr::read_file(file)
  sql <- glue::glue_sql(sql, ..., .con = .con, .envir = .envir)
}

# SQL files can be templated and called from R
sql <- read_sql(sql_template, make = c("Fiat X1-9", "Datsun 710"), .con = con)
DBI::dbGetQuery(con, sql) 
#>         make  mpg cyl disp hp drat    wt  qsec vs am gear carb
#> 1 Datsun 710 22.8   4  108 93 3.85 2.320 18.61  1  1    4    1
#> 2  Fiat X1-9 27.3   4   79 66 4.08 1.935 18.90  1  1    4    1

# All {values} must be provided, errors out
sql <- read_sql(sql_template, .con = con)
#> Error in eval(parse(text = text, keep.source = FALSE), envir): object 'make' not found

# Doesn't return anything
sql <- read_sql(sql_template, make = DBI::SQL(""), .con = con)
print(sql)
#> <SQL> SELECT * FROM mtcars WHERE make IN(  )
DBI::dbGetQuery(con, sql) 
#>  [1] make mpg  cyl  disp hp   drat wt   qsec vs   am   gear carb
#> <0 rows> (or 0-length row.names)

# Can't make the entire where clause a parameter either without doing a lot of escapes and basically defeating the purppose of glue
sql <- glue::glue_sql("SELECT * FROM mtcars {makes}",  makes = "WHERE make IN('Fiat X1-9', 'Datsun 710')", .con = con)
print(sql)
#> <SQL> SELECT * FROM mtcars 'WHERE make IN(''Fiat X1-9'', ''Datsun 710'')'
DBI::dbGetQuery(con, sql)
#>                   make  mpg cyl  disp  hp drat    wt  qsec vs am gear carb
#> 1            Mazda RX4 21.0   6 160.0 110 3.90 2.620 16.46  0  1    4    4
#> 2        Mazda RX4 Wag 21.0   6 160.0 110 3.90 2.875 17.02  0  1    4    4
#> 3           Datsun 710 22.8   4 108.0  93 3.85 2.320 18.61  1  1    4    1
#> 4       Hornet 4 Drive 21.4   6 258.0 110 3.08 3.215 19.44  1  0    3    1
#> 5    Hornet Sportabout 18.7   8 360.0 175 3.15 3.440 17.02  0  0    3    2
#> 6              Valiant 18.1   6 225.0 105 2.76 3.460 20.22  1  0    3    1
#> 7           Duster 360 14.3   8 360.0 245 3.21 3.570 15.84  0  0    3    4
#> 8            Merc 240D 24.4   4 146.7  62 3.69 3.190 20.00  1  0    4    2
#> 9             Merc 230 22.8   4 140.8  95 3.92 3.150 22.90  1  0    4    2
#> 10            Merc 280 19.2   6 167.6 123 3.92 3.440 18.30  1  0    4    4
#> 11           Merc 280C 17.8   6 167.6 123 3.92 3.440 18.90  1  0    4    4
#> 12          Merc 450SE 16.4   8 275.8 180 3.07 4.070 17.40  0  0    3    3
#> 13          Merc 450SL 17.3   8 275.8 180 3.07 3.730 17.60  0  0    3    3
#> 14         Merc 450SLC 15.2   8 275.8 180 3.07 3.780 18.00  0  0    3    3
#> 15  Cadillac Fleetwood 10.4   8 472.0 205 2.93 5.250 17.98  0  0    3    4
#> 16 Lincoln Continental 10.4   8 460.0 215 3.00 5.424 17.82  0  0    3    4
#> 17   Chrysler Imperial 14.7   8 440.0 230 3.23 5.345 17.42  0  0    3    4
#> 18            Fiat 128 32.4   4  78.7  66 4.08 2.200 19.47  1  1    4    1
#> 19         Honda Civic 30.4   4  75.7  52 4.93 1.615 18.52  1  1    4    2
#> 20      Toyota Corolla 33.9   4  71.1  65 4.22 1.835 19.90  1  1    4    1
#> 21       Toyota Corona 21.5   4 120.1  97 3.70 2.465 20.01  1  0    3    1
#> 22    Dodge Challenger 15.5   8 318.0 150 2.76 3.520 16.87  0  0    3    2
#> 23         AMC Javelin 15.2   8 304.0 150 3.15 3.435 17.30  0  0    3    2
#> 24          Camaro Z28 13.3   8 350.0 245 3.73 3.840 15.41  0  0    3    4
#> 25    Pontiac Firebird 19.2   8 400.0 175 3.08 3.845 17.05  0  0    3    2
#> 26           Fiat X1-9 27.3   4  79.0  66 4.08 1.935 18.90  1  1    4    1
#> 27       Porsche 914-2 26.0   4 120.3  91 4.43 2.140 16.70  0  1    5    2
#> 28        Lotus Europa 30.4   4  95.1 113 3.77 1.513 16.90  1  1    5    2
#> 29      Ford Pantera L 15.8   8 351.0 264 4.22 3.170 14.50  0  1    5    4
#> 30        Ferrari Dino 19.7   6 145.0 175 3.62 2.770 15.50  0  1    5    6
#> 31       Maserati Bora 15.0   8 301.0 335 3.54 3.570 14.60  0  1    5    8
#> 32          Volvo 142E 21.4   4 121.0 109 4.11 2.780 18.60  1  1    4    2

# Get all values first
all_makes <- DBI::dbGetQuery(con, "SELECT DISTINCT make FROM mtcars") %>% dplyr::pull(make)
sql <- read_sql(sql_template, make = all_makes, .con = con)
DBI::dbGetQuery(con, sql) 
#>                   make  mpg cyl  disp  hp drat    wt  qsec vs am gear carb
#> 1            Mazda RX4 21.0   6 160.0 110 3.90 2.620 16.46  0  1    4    4
#> 2        Mazda RX4 Wag 21.0   6 160.0 110 3.90 2.875 17.02  0  1    4    4
#> 3           Datsun 710 22.8   4 108.0  93 3.85 2.320 18.61  1  1    4    1
#> 4       Hornet 4 Drive 21.4   6 258.0 110 3.08 3.215 19.44  1  0    3    1
#> 5    Hornet Sportabout 18.7   8 360.0 175 3.15 3.440 17.02  0  0    3    2
#> 6              Valiant 18.1   6 225.0 105 2.76 3.460 20.22  1  0    3    1
#> 7           Duster 360 14.3   8 360.0 245 3.21 3.570 15.84  0  0    3    4
#> 8            Merc 240D 24.4   4 146.7  62 3.69 3.190 20.00  1  0    4    2
#> 9             Merc 230 22.8   4 140.8  95 3.92 3.150 22.90  1  0    4    2
#> 10            Merc 280 19.2   6 167.6 123 3.92 3.440 18.30  1  0    4    4
#> 11           Merc 280C 17.8   6 167.6 123 3.92 3.440 18.90  1  0    4    4
#> 12          Merc 450SE 16.4   8 275.8 180 3.07 4.070 17.40  0  0    3    3
#> 13          Merc 450SL 17.3   8 275.8 180 3.07 3.730 17.60  0  0    3    3
#> 14         Merc 450SLC 15.2   8 275.8 180 3.07 3.780 18.00  0  0    3    3
#> 15  Cadillac Fleetwood 10.4   8 472.0 205 2.93 5.250 17.98  0  0    3    4
#> 16 Lincoln Continental 10.4   8 460.0 215 3.00 5.424 17.82  0  0    3    4
#> 17   Chrysler Imperial 14.7   8 440.0 230 3.23 5.345 17.42  0  0    3    4
#> 18            Fiat 128 32.4   4  78.7  66 4.08 2.200 19.47  1  1    4    1
#> 19         Honda Civic 30.4   4  75.7  52 4.93 1.615 18.52  1  1    4    2
#> 20      Toyota Corolla 33.9   4  71.1  65 4.22 1.835 19.90  1  1    4    1
#> 21       Toyota Corona 21.5   4 120.1  97 3.70 2.465 20.01  1  0    3    1
#> 22    Dodge Challenger 15.5   8 318.0 150 2.76 3.520 16.87  0  0    3    2
#> 23         AMC Javelin 15.2   8 304.0 150 3.15 3.435 17.30  0  0    3    2
#> 24          Camaro Z28 13.3   8 350.0 245 3.73 3.840 15.41  0  0    3    4
#> 25    Pontiac Firebird 19.2   8 400.0 175 3.08 3.845 17.05  0  0    3    2
#> 26           Fiat X1-9 27.3   4  79.0  66 4.08 1.935 18.90  1  1    4    1
#> 27       Porsche 914-2 26.0   4 120.3  91 4.43 2.140 16.70  0  1    5    2
#> 28        Lotus Europa 30.4   4  95.1 113 3.77 1.513 16.90  1  1    5    2
#> 29      Ford Pantera L 15.8   8 351.0 264 4.22 3.170 14.50  0  1    5    4
#> 30        Ferrari Dino 19.7   6 145.0 175 3.62 2.770 15.50  0  1    5    6
#> 31       Maserati Bora 15.0   8 301.0 335 3.54 3.570 14.60  0  1    5    8
#> 32          Volvo 142E 21.4   4 121.0 109 4.11 2.780 18.60  1  1    4    2

# Templating with a conditional#### 
sql <- "SELECT * FROM mtcars WHERE cyl >= {cyl} "
sql_template <- tempfile(fileext = ".sql")
readr::write_file(sql, sql_template)
read_sql <- function(file, ..., .con, .envir = parent.frame()){
  sql <- readr::read_file(file)
  sql <- glue::glue_sql(sql, ..., .con = .con, .envir = .envir)
}

# No way to use the all values approach since it's a one sided conditional 
sql <- read_sql(sql_template, cyl = 8, .con = con)
DBI::dbGetQuery(con, sql) 
#>                   make  mpg cyl  disp  hp drat    wt  qsec vs am gear carb
#> 1    Hornet Sportabout 18.7   8 360.0 175 3.15 3.440 17.02  0  0    3    2
#> 2           Duster 360 14.3   8 360.0 245 3.21 3.570 15.84  0  0    3    4
#> 3           Merc 450SE 16.4   8 275.8 180 3.07 4.070 17.40  0  0    3    3
#> 4           Merc 450SL 17.3   8 275.8 180 3.07 3.730 17.60  0  0    3    3
#> 5          Merc 450SLC 15.2   8 275.8 180 3.07 3.780 18.00  0  0    3    3
#> 6   Cadillac Fleetwood 10.4   8 472.0 205 2.93 5.250 17.98  0  0    3    4
#> 7  Lincoln Continental 10.4   8 460.0 215 3.00 5.424 17.82  0  0    3    4
#> 8    Chrysler Imperial 14.7   8 440.0 230 3.23 5.345 17.42  0  0    3    4
#> 9     Dodge Challenger 15.5   8 318.0 150 2.76 3.520 16.87  0  0    3    2
#> 10         AMC Javelin 15.2   8 304.0 150 3.15 3.435 17.30  0  0    3    2
#> 11          Camaro Z28 13.3   8 350.0 245 3.73 3.840 15.41  0  0    3    4
#> 12    Pontiac Firebird 19.2   8 400.0 175 3.08 3.845 17.05  0  0    3    2
#> 13      Ford Pantera L 15.8   8 351.0 264 4.22 3.170 14.50  0  1    5    4
#> 14       Maserati Bora 15.0   8 301.0 335 3.54 3.570 14.60  0  1    5    8

Answer 1

glue::glue_sql 可以使用多个参数:

# con <- dbConnect(...)
make <- c()
glue::glue_sql(
  "select * from mtcars",
  if (length(make)) " where make in ({make*})" else "",
  .con = con)
# <SQL> select * from mtcars

make <- c("Fiat X1-9", "Datsun 710")
glue::glue_sql(                                          # unchanged
  "select * from mtcars",
  if (length(make)) " where make in ({make*})" else "",
  .con = con)
# <SQL> select * from mtcars where make in ('Fiat X1-9', 'Datsun 710')