fkeck · Oct 8, 2026 · Mar 16, 2026 · Mar 17, 2026 · Mar 17, 2026 · Mar 20, 2026
diff --git a/R/utils_regexes.R b/R/utils_regexes.R
@@ -32,6 +32,18 @@
   return(x)
 }
 
+#' Extract season number from file paths
+#'
+#' Parses the file name component of each path and attempts to detect the season
+#' number using four common naming conventions:
+#' \code{S01}, \code{SEASON.2}, \code{S03E05}, and \code{2X05}.
+#' Returns \code{NA} for paths where no convention matches.
+#'
+#' @param x a character vector of file or directory paths.
+#'
+#' @returns A numeric vector of season numbers, the same length as \code{x}.
+#'
+#' @noRd
 # Guess subtitle format from subtitle content when no file extension is
 # available, e.g. when parsing literal text.
 .guess_subtitle_format <- function(x) {

diff --git a/README.Rmd b/README.Rmd
@@ -37,7 +37,7 @@ if (coverage >= 90) {
 
 [![Project Status: Active – The project has reached a stable, usable state and is being actively developed.](https://www.repostatus.org/badges/latest/active.svg)](https://www.repostatus.org/#active)
 [![R-CMD-check](https://github.com/fkeck/subtools/actions/workflows/check-standard.yml/badge.svg)](https://github.com/fkeck/subtools/actions/workflows/check-standard.yml)
-[![Code Coverage: `r coverage`%](https://img.shields.io/badge/code_coverage-`r coverage`%25-`r colour`)](https://img.shields.io/badge/code_coverage-`r coverage`%25-`r colour`)
+![Code Coverage: `r coverage`%](https://img.shields.io/badge/code_coverage-`r coverage`%25-`r colour`)
 
 ### Read, write and manipulate subtitles in R
 
@@ -48,11 +48,7 @@ Subtools is a R package to read, write and manipulate subtitles in R. This then
 ### Install
 You can install the package directly from CRAN with `install.packages("subtools")` or get the latest, in development, version with:
 ```{r, eval = FALSE}
-remotes::install_github(
-  repo = "fkeck/subtools@dev",
-  build_manual = TRUE,
-  build_vignettes = TRUE
-)
+pak::pkg_install("fkeck/subtools@dev")
 ```
 
 ```{r}

diff --git a/README.md b/README.md
@@ -9,8 +9,8 @@
 state and is being actively
 developed.](https://www.repostatus.org/badges/latest/active.svg)](https://www.repostatus.org/#active)
 [![R-CMD-check](https://github.com/fkeck/subtools/actions/workflows/check-standard.yml/badge.svg)](https://github.com/fkeck/subtools/actions/workflows/check-standard.yml)
-[![Code Coverage:
-82%](https://img.shields.io/badge/code_coverage-82%25-green)](https://img.shields.io/badge/code_coverage-82%25-green)
+![Code Coverage:
+82%](https://img.shields.io/badge/code_coverage-82%25-green)
 
 ### Read, write and manipulate subtitles in R
 
@@ -30,11 +30,7 @@ You can install the package directly from CRAN with
 version with:
 
 ``` r
-remotes::install_github(
-  repo = "fkeck/subtools@dev",
-  build_manual = TRUE,
-  build_vignettes = TRUE
-)
+pak::pkg_install("fkeck/subtools@dev")
 ```
 
 ``` r
@@ -242,18 +238,56 @@ rushmore_sub
 unnest_tokens(rushmore_sub)
 #> # A tibble: 49 × 4
 #>    ID    Timecode_in Timecode_out Text_content
-#>    <chr> <time>      <time>       <chr>
-#>  1 180   20'40.9700" 20'41.4858"  rushmore
-#>  2 180   20'41.4868" 20'42.0026"  deserves
-#>  3 180   20'42.0036" 20'42.1318"  an
-#>  4 180   20'42.1328" 20'42.6486"  aquarium
-#>  5 180   20'42.6496" 20'42.7132"  a
-#>  6 180   20'42.7142" 20'43.0363"  first
-#>  7 180   20'43.0373" 20'43.3593"  class
-#>  8 180   20'43.3603" 20'43.8761"  aquarium
-#>  9 180   20'43.8771" 20'44.1991"  where
-#> 10 180   20'44.2001" 20'44.8451"  scientists
-#> # ℹ 39 more rows
+#>    <chr> <time>      <time>       <chr>       
+#>  1 180   20'40.9700" 20'41.4858"  rushmore    
+#>  2 180   20'41.4868" 20'42.0026"  deserves    
+#>  3 180   20'42.0036" 20'42.1318"  an          
+#>  4 180   20'42.1328" 20'42.6486"  aquarium    
+#>  5 180   20'42.6496" 20'42.7132"  a           
+#>  6 180   20'42.7142" 20'43.0363"  first       
+#>  7 180   20'43.0373" 20'43.3593"  class       
+#>  8 180   20'43.3603" 20'43.8761"  aquarium    
+#>  9 180   20'43.8771" 20'44.1991"  where       
+#> 10 180   20'44.2001" 20'44.8451"  scientists  
+#> 11 180   20'44.8461" 20'45.0389"  can         
+#> 12 180   20'45.0399" 20'45.4911"  lecture     
+#> 13 180   20'45.4921" 20'45.6849"  and         
+#> 14 180   20'45.6859" 20'46.2017"  students    
+#> 15 180   20'46.2027" 20'46.3955"  can         
+#> 16 180   20'46.3965" 20'46.8478"  observe     
+#> 17 180   20'46.8488" 20'47.2354"  marine      
+#> 18 180   20'47.2364" 20'47.4938"  life        
+#> 19 180   20'47.4948" 20'47.6230"  in          
+#> 20 180   20'47.6240" 20'47.8168"  its         
+#> 21 180   20'47.8178" 20'48.2690"  natural     
+#> 22 181   20'48.2700" 20'48.3393"  i           
+#> 23 181   20'48.3403" 20'48.6908"  don't       
+#> 24 181   20'48.6918" 20'48.9720"  know        
+#> 25 181   20'48.9730" 20'49.2532"  what        
+#> 26 181   20'49.2542" 20'49.3938"  do          
+#> 27 181   20'49.3948" 20'49.6046"  you         
+#> 28 181   20'49.6056" 20'49.9561"  think       
+#> 29 181   20'49.9571" 20'50.3076"  ernie       
+#> 30 181   20'50.3086" 20'50.8700"  aquarium    
+#> 31 182   20'50.9470" 20'51.4402"  what        
+#> 32 182   20'51.4412" 20'51.9343"  kind        
+#> 33 182   20'51.9353" 20'52.1814"  of          
+#> 34 182   20'52.1824" 20'52.6755"  fish        
+#> 35 182   20'52.6765" 20'53.9109"  barracudas  
+#> 36 182   20'53.9119" 20'55.0228"  stingrays   
+#> 37 182   20'55.0238" 20'56.3817"  hammerheads 
+#> 38 182   20'56.3827" 20'57.3700"  piranhas    
+#> 39 183   20'58.0520" 20'58.6840"  piranhas    
+#> 40 183   20'58.6850" 20'59.1588"  really      
+#> 41 183   20'59.1598" 20'59.3962"  yes         
+#> 42 183   20'59.3972" 20'59.6336"  i'm         
+#> 43 183   20'59.6346" 21'00.1874"  talking     
+#> 44 183   21'00.1884" 21'00.3457"  to          
+#> 45 183   21'00.3467" 21'00.4248"  a           
+#> 46 183   21'00.4258" 21'00.6622"  guy         
+#> 47 183   21'00.6632" 21'00.8205"  in          
+#> 48 183   21'00.8215" 21'01.2161"  south       
+#> 49 183   21'01.2171" 21'01.7700"  america
 
 unnest_tokens(bb_sub_clean, token = "sentences")
 #> # A tibble: 8 × 7
@@ -286,7 +320,7 @@ Note that these project used the branch 0.x of `subtools`. The API is
 totally different from `subtools 1.0`.
 
 [*You beautiful, naïve, sophisticated newborn
-series*](https://www.masalmon.eu/2017/11/05/newborn-serie/) by
+series*](https://masalmon.eu/2017/11/05/newborn-serie/) by
 [ma_salmon](https://x.com/ma_salmon)
 
 [*A tidy text analysis of Rick and

diff --git a/tests/testthat/_snaps/unnest_tokens.md b/tests/testthat/_snaps/unnest_tokens.md
@@ -4,17 +4,42 @@
       unnest_tokens(tbl = s)
     Output
       # A tibble: 36 x 5
-         ID    Timecode_in Timecode_out Text_content test 
-         <chr> <time>      <time>       <chr>        <chr>
-       1 1     00'01.0010" 00'01.6250"  never        Test 
-       2 1     00'01.6260" 00'02.2500"  drink        Test 
-       3 1     00'02.2510" 00'03.0000"  liquid       Test 
-       4 1     00'03.0010" 00'04.0000"  nitrogen     Test 
-       5 2     00'05.0010" 00'05.2162"  it           Test 
-       6 2     00'05.2172" 00'05.6486"  will         Test 
-       7 2     00'05.6496" 00'06.6216"  perforate    Test 
-       8 2     00'06.6226" 00'07.0541"  your         Test 
-       9 2     00'07.0551" 00'07.8108"  stomach      Test 
-      10 2     00'07.8118" 00'08.1351"  you          Test 
-      # i 26 more rows
+         ID              Timecode_in Timecode_out Text_content test 
+         <chr>           <time>      <time>       <chr>        <chr>
+       1 1               00'01.0010" 00'01.6250"  never        Test 
+       2 1               00'01.6260" 00'02.2500"  drink        Test 
+       3 1               00'02.2510" 00'03.0000"  liquid       Test 
+       4 1               00'03.0010" 00'04.0000"  nitrogen     Test 
+       5 2               00'05.0010" 00'05.2162"  it           Test 
+       6 2               00'05.2172" 00'05.6486"  will         Test 
+       7 2               00'05.6496" 00'06.6216"  perforate    Test 
+       8 2               00'06.6226" 00'07.0541"  your         Test 
+       9 2               00'07.0551" 00'07.8108"  stomach      Test 
+      10 2               00'07.8118" 00'08.1351"  you          Test 
+      11 2               00'08.1361" 00'08.6757"  could        Test 
+      12 2               00'08.6767" 00'09.0000"  die          Test 
+      13 A dangerous cue 00'11.0010" 00'11.0989"  dès          Test 
+      14 A dangerous cue 00'11.0999" 00'11.2308"  noël         Test 
+      15 A dangerous cue 00'11.2318" 00'11.2967"  où           Test 
+      16 A dangerous cue 00'11.2977" 00'11.3626"  un           Test 
+      17 A dangerous cue 00'11.3636" 00'11.5604"  zéphyr       Test 
+      18 A dangerous cue 00'11.5614" 00'11.6593"  haï          Test 
+      19 A dangerous cue 00'11.6603" 00'11.7253"  me           Test 
+      20 A dangerous cue 00'11.7263" 00'11.8242"  vêt          Test 
+      21 A dangerous cue 00'11.8252" 00'11.8901"  de           Test 
+      22 A dangerous cue 00'11.8911" 00'12.1209"  glaçons      Test 
+      23 A dangerous cue 00'12.1219" 00'12.3846"  würmiens     Test 
+      24 A dangerous cue 00'12.3856" 00'12.4505"  je           Test 
+      25 A dangerous cue 00'12.4515" 00'12.5824"  dîne         Test 
+      26 A dangerous cue 00'12.5834" 00'12.8462"  d’exquis     Test 
+      27 A dangerous cue 00'12.8472" 00'13.0110"  rôtis        Test 
+      28 A dangerous cue 00'13.0120" 00'13.0769"  de           Test 
+      29 A dangerous cue 00'13.0779" 00'13.2088"  bœuf         Test 
+      30 A dangerous cue 00'13.2098" 00'13.2747"  au           Test 
+      31 A dangerous cue 00'13.2757" 00'13.3736"  kir          Test 
+      32 A dangerous cue 00'13.3746" 00'13.4066"  à            Test 
+      33 A dangerous cue 00'13.4076" 00'13.5385"  l’aÿ         Test 
+      34 A dangerous cue 00'13.5395" 00'13.7033"  d’âge        Test 
+      35 A dangerous cue 00'13.7043" 00'13.8022"  mûr          Test 
+      36 A dangerous cue 00'13.8032" 00'14.0000"  cætera       Test