add textgrid_to_df() function

ropensci · Jun 7, 2020 · 8043a55 · 8043a55
1 parent f07d035
commit 8043a55
Show file tree

Hide file tree

Showing 7 changed files with 80 additions and 2 deletions.
diff --git a/NAMESPACE b/NAMESPACE
@@ -19,6 +19,7 @@ export(get_textgrid_names)
 export(rename_soundfiles)
 export(rename_videofiles)
 export(set_textgrid_names)
+export(textgrid_to_df)
 export(tier_to_df)
 importFrom(grDevices,dev.off)
 importFrom(grDevices,png)

diff --git a/NEWS b/NEWS
@@ -1,4 +1,5 @@
 phonfieldwork 0.0.5 (07.06.2020)
+  - add "textgrid_to_df()" function for reading Praat files
   - add "create_glossed_document()" function for converting .flextext files into a glossed document
   - add "flextext_to_df()" function for reading FLEx files
   - add "eaf_to_df()" function for reading ELAN files

diff --git a/R/textgrid_to_df.R b/R/textgrid_to_df.R
@@ -0,0 +1,37 @@
+#' TextGrid to dataframe
+#'
+#' Convert Praat TextGrid to a dataframe.
+#'
+#' @author George Moroz <[email protected]>
+#'
+#' @param textgrid string with a filename or path to the TextGrid
+#' @return a dataframe with columns:  \code{id}, \code{start}, \code{end} (if it is an interval tier -- the same as the start value), \code{annotation}, and \code{tier}
+#'
+#' @examples
+#' textgrid_to_df(example_textgrid)
+#'
+#' @export
+
+textgrid_to_df <- function(textgrid, tier = 1){
+  if(grepl("TextGrid", textgrid[2])){
+    tg <- textgrid
+  } else{
+    tg <- readLines(textgrid)
+  }
+  n_tiers <- as.double(regmatches(tg[7], regexpr("\\d", tg[7])))
+  lapply(1:n_tiers, function(x){
+    df <- phonfieldwork::tier_to_df(tg, x)
+    df$tier <- x
+    if(!("end" %in% names(df))){
+      df <- data.frame(id = df$id,
+                       start = df$start,
+                       end = df$start,
+                       annotation = df$annotation,
+                       tier = df$tier)
+    }
+    return(df)
+  }) ->
+    l
+  result <- Reduce(rbind, l)
+  return(result[order(result$start),])
+}
diff --git a/docs/index.Rmd b/docs/index.Rmd
@@ -341,6 +341,12 @@ You can find the created example [here](https://agricolamz.github.io/phonfieldwo
 
 The `phonfieldwork` package provides also several methods for reading several file types into R (just change the `system.file()` function to path to the file):
 
+* file `.TextGrid` from Praat
+```{r}
+textgrid_to_df(example_textgrid)
+```
+
+
 * file `.eaf` from ELAN
 ```{r}
 eaf_to_df(system.file("extdata", "test.eaf", package = "phonfieldwork"))

diff --git a/docs/index.html b/docs/index.html
@@ -1993,6 +1993,15 @@ <h2><span class="header-section-number">4.8</span> Create a viewer</h2>
 <h2><span class="header-section-number">4.9</span> Read files to R</h2>
 <p>The <code>phonfieldwork</code> package provides also several methods for reading several file types into R (just change the <code>system.file()</code> function to path to the file):</p>
 <ul>
+<li>file <code>.TextGrid</code> from Praat</li>
+</ul>
+<pre class="r"><code>textgrid_to_df(example_textgrid)</code></pre>
+<div data-pagedtable="false">
+<script data-pagedtable-source type="application/json">
+{"columns":[{"label":[""],"name":["_rn_"],"type":[""],"align":["left"]},{"label":["id"],"name":[1],"type":["int"],"align":["right"]},{"label":["start"],"name":[2],"type":["dbl"],"align":["right"]},{"label":["end"],"name":[3],"type":["dbl"],"align":["right"]},{"label":["annotation"],"name":[4],"type":["chr"],"align":["left"]},{"label":["tier"],"name":[5],"type":["int"],"align":["right"]}],"data":[{"1":"1","2":"0.00000000","3":"0.01246583","4":"","5":"1","_rn_":"1"},{"1":"1","2":"0.00000000","3":"0.01246583","4":"","5":"2","_rn_":"6"},{"1":"2","2":"0.01246583","3":"0.24781914","4":"t","5":"1","_rn_":"2"},{"1":"2","2":"0.01246583","3":"0.24781914","4":"","5":"2","_rn_":"7"},{"1":"1","2":"0.01246583","3":"0.01246583","4":"t","5":"3","_rn_":"11"},{"1":"3","2":"0.24781914","3":"0.39552363","4":"e","5":"1","_rn_":"3"},{"1":"3","2":"0.24781914","3":"0.39552363","4":"","5":"2","_rn_":"8"},{"1":"2","2":"0.24781914","3":"0.24781914","4":"e","5":"3","_rn_":"12"},{"1":"4","2":"0.39552363","3":"0.51157715","4":"s","5":"1","_rn_":"4"},{"1":"4","2":"0.39552363","3":"0.51157715","4":"","5":"2","_rn_":"9"},{"1":"3","2":"0.39552363","3":"0.39552363","4":"s","5":"3","_rn_":"13"},{"1":"5","2":"0.51157715","3":"0.65267574","4":"t","5":"1","_rn_":"5"},{"1":"5","2":"0.51157715","3":"0.65267574","4":"","5":"2","_rn_":"10"},{"1":"4","2":"0.51157715","3":"0.51157715","4":"t","5":"3","_rn_":"14"}],"options":{"columns":{"min":{},"max":[10]},"rows":{"min":[10],"max":[10]},"pages":{}}}
+  </script>
+</div>
+<ul>
 <li>file <code>.eaf</code> from ELAN</li>
 </ul>
 <pre class="r"><code>eaf_to_df(system.file(&quot;extdata&quot;, &quot;test.eaf&quot;, package = &quot;phonfieldwork&quot;))</code></pre>

diff --git a/docs/s1/stimuli_viewer.html b/docs/s1/stimuli_viewer.html
@@ -3252,8 +3252,8 @@ <h1 class="title toc-ignore">Sound Viewer</h1>
 <h1></h1>
 <div id="data" class="section level2">
 <h2>data</h2>
-<div id="htmlwidget-856cf1ed3cd37610ff04" style="width:100%;height:auto;" class="datatables html-widget"></div>
-<script type="application/json" data-for="htmlwidget-856cf1ed3cd37610ff04">{"x":{"filter":"top","filterHTML":"<tr>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n<\/tr>","data":[["tip <a onmouseover=\"resize(this, '200%')\" onmouseout=\"resize(this, '100%')\" onclick = 'pic_appear(\"s1_pics/1_s1_ı.png\", \"tip\")'> &#x1f441;<a> <a onmouseover=\"resize(this, '200%')\" onmouseout=\"resize(this, '100%')\" onclick = 'sound_play(\"s1_sounds/1_s1_ı.wav\")'> &#x1f442;<a>","tap <a onmouseover=\"resize(this, '200%')\" onmouseout=\"resize(this, '100%')\" onclick = 'pic_appear(\"s1_pics/2_s1_æ.png\", \"tap\")'> &#x1f441;<a> <a onmouseover=\"resize(this, '200%')\" onmouseout=\"resize(this, '100%')\" onclick = 'sound_play(\"s1_sounds/2_s1_æ.wav\")'> &#x1f442;<a>","top <a onmouseover=\"resize(this, '200%')\" onmouseout=\"resize(this, '100%')\" onclick = 'pic_appear(\"s1_pics/3_s1_ɒ.png\", \"top\")'> &#x1f441;<a> <a onmouseover=\"resize(this, '200%')\" onmouseout=\"resize(this, '100%')\" onclick = 'sound_play(\"s1_sounds/3_s1_ɒ.wav\")'> &#x1f442;<a>"],["ı","æ","ɒ"]],"container":"<table class=\"display\">\n  <thead>\n    <tr>\n      <th>labels<\/th>\n      <th>X2<\/th>\n    <\/tr>\n  <\/thead>\n<\/table>","options":{"pageLength":50,"dom":"tip","order":[],"autoWidth":false,"orderClasses":false,"orderCellsTop":true}},"evals":[],"jsHooks":[]}</script>
+<div id="htmlwidget-bef8bd1f9fcd817c372f" style="width:100%;height:auto;" class="datatables html-widget"></div>
+<script type="application/json" data-for="htmlwidget-bef8bd1f9fcd817c372f">{"x":{"filter":"top","filterHTML":"<tr>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n<\/tr>","data":[["tip <a onmouseover=\"resize(this, '200%')\" onmouseout=\"resize(this, '100%')\" onclick = 'pic_appear(\"s1_pics/1_s1_ı.png\", \"tip\")'> &#x1f441;<a> <a onmouseover=\"resize(this, '200%')\" onmouseout=\"resize(this, '100%')\" onclick = 'sound_play(\"s1_sounds/1_s1_ı.wav\")'> &#x1f442;<a>","tap <a onmouseover=\"resize(this, '200%')\" onmouseout=\"resize(this, '100%')\" onclick = 'pic_appear(\"s1_pics/2_s1_æ.png\", \"tap\")'> &#x1f441;<a> <a onmouseover=\"resize(this, '200%')\" onmouseout=\"resize(this, '100%')\" onclick = 'sound_play(\"s1_sounds/2_s1_æ.wav\")'> &#x1f442;<a>","top <a onmouseover=\"resize(this, '200%')\" onmouseout=\"resize(this, '100%')\" onclick = 'pic_appear(\"s1_pics/3_s1_ɒ.png\", \"top\")'> &#x1f441;<a> <a onmouseover=\"resize(this, '200%')\" onmouseout=\"resize(this, '100%')\" onclick = 'sound_play(\"s1_sounds/3_s1_ɒ.wav\")'> &#x1f442;<a>"],["ı","æ","ɒ"]],"container":"<table class=\"display\">\n  <thead>\n    <tr>\n      <th>labels<\/th>\n      <th>X2<\/th>\n    <\/tr>\n  <\/thead>\n<\/table>","options":{"pageLength":50,"dom":"tip","order":[],"autoWidth":false,"orderClasses":false,"orderCellsTop":true}},"evals":[],"jsHooks":[]}</script>
 <div id="my_block" class="my_block" onclick="pic_disappear()">
 <span class="close">×</span> <img class="my_img" id="my_img">
 <div id="caption" class="caption">

diff --git a/man/textgrid_to_df.Rd b/man/textgrid_to_df.Rd