Merge pull request #272 from Roche/dev

Dev

Author: ofajardo

CITATION.cff

@@ -5,7 +5,7 @@ authors:
   given-names: "Otto"
   orcid: "https://orcid.org/0000-0002-3363-9287"
 title: "Pyreadstat"
-version: 1.2.7
+version: 1.2.8
 doi: 10.5281/zenodo.6612282
 date-released: 2018-09-24
 url: "https://github.com/Roche/pyreadstat"

README.md

@@ -16,6 +16,9 @@ If you would like to read R RData and Rds files into python in an easy way,
 take a look to [pyreadr](https://github.com/ofajardo/pyreadr), a wrapper
 around the C library [librdata](https://github.com/WizardMac/librdata)
 
+If you would like to effortlessly produce beautiful summaries from pandas dataframes take
+a look to [pysummaries](https://github.com/Genentech/pysummaries)!
+
 
 **DISCLAIMER**
 

change_log.md

@@ -1,3 +1,9 @@
+# 1.2.8 (github, pypi and conda 2024.10.18)
+* Added Multiple Reponse Data Sets for SAV files #259
+* Fixed pyreadstat not raising error if folder does not exists when writing #269
+* Fixed tests for numpy 2 changes # 266
+* Readstat sources updated to commit ba4392e9d48c4d997d2737719f4cf6320fb66990 on dev branch
+
 # 1.2.7 (github, pypi and conda 2024.03.14)
 * Fixing warnings in new pandas version 2.2.1 fixes #252
 * Remove string encoding for read_por fixes #253

docs/_build/doctrees/environment.pickle

@@ -1,4 +1,4 @@
 # Sphinx build info version 1
 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: f22f85c58ffb6d644f63f9173b9d1b95
+config: 3684e396bb8bf7df6bbcdabbae81c680
 tags: 645f666f9bcd5a90fca523b33c5a78b7

docs/_build/doctrees/index.doctree

@@ -52,6 +52,13 @@ object contains the following fields:
   * variable_storage_width: a dict with keys being variable names and values being the storage width
   * variable_display_width: a dict with keys being variable names and values being the display width
   * variable_measure: a dict with keys being variable names and values being the measure: nominal, ordinal, scale or unknown
+  * mr_sets: a dictionary representing the definitions of multiple-response (MR)
+    variables in the dataset (currently only supported for SAV format). MR variables
+    are arrays composed of several other variables. This metadata entry, `mr_sets`,
+    specifies which variables are combined to form each array. Each entry includes:
+    `type`, `is_dichotomy`, `counted_value`, `label`, and `variable_list`. The meaning
+    of these fields is based on the SPSS specification for multiple-response sets.
+
 
 There are two functions to deal with value labels: set_value_labels and set_catalog_to_sas. You can read about them
 in the next section.

docs/_build/html/.buildinfo

@@ -4,7 +4,7 @@
  *
  * Sphinx stylesheet -- basic theme.
  *
- * :copyright: Copyright 2007-2023 by the Sphinx team, see AUTHORS.
+ * :copyright: Copyright 2007-2024 by the Sphinx team, see AUTHORS.
  * :license: BSD, see LICENSE for details.
  *
  */

docs/_build/html/_sources/index.rst.txt

@@ -4,7 +4,7 @@
  *
  * Base JavaScript utilities for all Sphinx HTML documentation.
  *
- * :copyright: Copyright 2007-2023 by the Sphinx team, see AUTHORS.
+ * :copyright: Copyright 2007-2024 by the Sphinx team, see AUTHORS.
  * :license: BSD, see LICENSE for details.
  *
  */

docs/_build/html/_static/basic.css

@@ -1,5 +1,5 @@
 const DOCUMENTATION_OPTIONS = {
-    VERSION: '1.2.7',
+    VERSION: '1.2.8',
     LANGUAGE: 'en',
     COLLAPSE_INDEX: false,
     BUILDER: 'html',

docs/_build/html/_static/doctools.js

@@ -5,15 +5,15 @@
  * This script contains the language-specific data used by searchtools.js,
  * namely the list of stopwords, stemmer, scorer and splitter.
  *
- * :copyright: Copyright 2007-2023 by the Sphinx team, see AUTHORS.
+ * :copyright: Copyright 2007-2024 by the Sphinx team, see AUTHORS.
  * :license: BSD, see LICENSE for details.
  *
  */
 
 var stopwords = ["a", "and", "are", "as", "at", "be", "but", "by", "for", "if", "in", "into", "is", "it", "near", "no", "not", "of", "on", "or", "such", "that", "the", "their", "then", "there", "these", "they", "this", "to", "was", "will", "with"];
 
 
-/* Non-minified version is copied as a separate JS file, is available */
+/* Non-minified version is copied as a separate JS file, if available */
 
 /**
  * Porter Stemmer

docs/_build/html/_static/documentation_options.js

@@ -4,7 +4,7 @@
  *
  * Sphinx JavaScript utilities for the full-text search.
  *
- * :copyright: Copyright 2007-2023 by the Sphinx team, see AUTHORS.
+ * :copyright: Copyright 2007-2024 by the Sphinx team, see AUTHORS.
  * :license: BSD, see LICENSE for details.
  *
  */
@@ -99,7 +99,7 @@ const _displayItem = (item, searchTerms, highlightTerms) => {
       .then((data) => {
         if (data)
           listItem.appendChild(
-            Search.makeSearchSummary(data, searchTerms)
+            Search.makeSearchSummary(data, searchTerms, anchor)
           );
         // highlight search terms in the summary
         if (SPHINX_HIGHLIGHT_ENABLED)  // set in sphinx_highlight.js
@@ -116,8 +116,8 @@ const _finishSearch = (resultCount) => {
     );
   else
     Search.status.innerText = _(
-      `Search finished, found ${resultCount} page(s) matching the search query.`
-    );
+      "Search finished, found ${resultCount} page(s) matching the search query."
+    ).replace('${resultCount}', resultCount);
 };
 const _displayNextItem = (
   results,
@@ -137,6 +137,22 @@ const _displayNextItem = (
   // search finished, update title and status message
   else _finishSearch(resultCount);
 };
+// Helper function used by query() to order search results.
+// Each input is an array of [docname, title, anchor, descr, score, filename].
+// Order the results by score (in opposite order of appearance, since the
+// `_displayNextItem` function uses pop() to retrieve items) and then alphabetically.
+const _orderResultsByScoreThenName = (a, b) => {
+  const leftScore = a[4];
+  const rightScore = b[4];
+  if (leftScore === rightScore) {
+    // same score: sort alphabetically
+    const leftTitle = a[1].toLowerCase();
+    const rightTitle = b[1].toLowerCase();
+    if (leftTitle === rightTitle) return 0;
+    return leftTitle > rightTitle ? -1 : 1; // inverted is intentional
+  }
+  return leftScore > rightScore ? 1 : -1;
+};
 
 /**
  * Default splitQuery function. Can be overridden in ``sphinx.search`` with a
@@ -160,13 +176,26 @@ const Search = {
   _queued_query: null,
   _pulse_status: -1,
 
-  htmlToText: (htmlString) => {
+  htmlToText: (htmlString, anchor) => {
     const htmlElement = new DOMParser().parseFromString(htmlString, 'text/html');
-    htmlElement.querySelectorAll(".headerlink").forEach((el) => { el.remove() });
+    for (const removalQuery of [".headerlink", "script", "style"]) {
+      htmlElement.querySelectorAll(removalQuery).forEach((el) => { el.remove() });
+    }
+    if (anchor) {
+      const anchorContent = htmlElement.querySelector(`[role="main"] ${anchor}`);
+      if (anchorContent) return anchorContent.textContent;
+
+      console.warn(
+        `Anchored content block not found. Sphinx search tries to obtain it via DOM query '[role=main] ${anchor}'. Check your theme or template.`
+      );
+    }
+
+    // if anchor not specified or not found, fall back to main content
     const docContent = htmlElement.querySelector('[role="main"]');
-    if (docContent !== undefined) return docContent.textContent;
+    if (docContent) return docContent.textContent;
+
     console.warn(
-      "Content block not found. Sphinx search tries to obtain it via '[role=main]'. Could you check your theme or template."
+      "Content block not found. Sphinx search tries to obtain it via DOM query '[role=main]'. Check your theme or template."
     );
     return "";
   },
@@ -239,16 +268,7 @@ const Search = {
     else Search.deferQuery(query);
   },
 
-  /**
-   * execute search (requires search index to be loaded)
-   */
-  query: (query) => {
-    const filenames = Search._index.filenames;
-    const docNames = Search._index.docnames;
-    const titles = Search._index.titles;
-    const allTitles = Search._index.alltitles;
-    const indexEntries = Search._index.indexentries;
-
+  _parseQuery: (query) => {
     // stem the search terms and add them to the correct list
     const stemmer = new Stemmer();
     const searchTerms = new Set();
@@ -284,21 +304,38 @@ const Search = {
     // console.info("required: ", [...searchTerms]);
     // console.info("excluded: ", [...excludedTerms]);
 
-    // array of [docname, title, anchor, descr, score, filename]
-    let results = [];
+    return [query, searchTerms, excludedTerms, highlightTerms, objectTerms];
+  },
+
+  /**
+   * execute search (requires search index to be loaded)
+   */
+  _performSearch: (query, searchTerms, excludedTerms, highlightTerms, objectTerms) => {
+    const filenames = Search._index.filenames;
+    const docNames = Search._index.docnames;
+    const titles = Search._index.titles;
+    const allTitles = Search._index.alltitles;
+    const indexEntries = Search._index.indexentries;
+
+    // Collect multiple result groups to be sorted separately and then ordered.
+    // Each is an array of [docname, title, anchor, descr, score, filename].
+    const normalResults = [];
+    const nonMainIndexResults = [];
+
     _removeChildren(document.getElementById("search-progress"));
 
-    const queryLower = query.toLowerCase();
+    const queryLower = query.toLowerCase().trim();
     for (const [title, foundTitles] of Object.entries(allTitles)) {
-      if (title.toLowerCase().includes(queryLower) && (queryLower.length >= title.length/2)) {
+      if (title.toLowerCase().trim().includes(queryLower) && (queryLower.length >= title.length/2)) {
         for (const [file, id] of foundTitles) {
-          let score = Math.round(100 * queryLower.length / title.length)
-          results.push([
+          const score = Math.round(Scorer.title * queryLower.length / title.length);
+          const boost = titles[file] === title ? 1 : 0;  // add a boost for document titles
+          normalResults.push([
             docNames[file],
             titles[file] !== title ? `${titles[file]} > ${title}` : title,
             id !== null ? "#" + id : "",
             null,
-            score,
+            score + boost,
             filenames[file],
           ]);
         }
@@ -308,46 +345,47 @@ const Search = {
     // search for explicit entries in index directives
     for (const [entry, foundEntries] of Object.entries(indexEntries)) {
       if (entry.includes(queryLower) && (queryLower.length >= entry.length/2)) {
-        for (const [file, id] of foundEntries) {
-          let score = Math.round(100 * queryLower.length / entry.length)
-          results.push([
+        for (const [file, id, isMain] of foundEntries) {
+          const score = Math.round(100 * queryLower.length / entry.length);
+          const result = [
             docNames[file],
             titles[file],
             id ? "#" + id : "",
             null,
             score,
             filenames[file],
-          ]);
+          ];
+          if (isMain) {
+            normalResults.push(result);
+          } else {
+            nonMainIndexResults.push(result);
+          }
         }
       }
     }
 
     // lookup as object
     objectTerms.forEach((term) =>
-      results.push(...Search.performObjectSearch(term, objectTerms))
+      normalResults.push(...Search.performObjectSearch(term, objectTerms))
     );
 
     // lookup as search terms in fulltext
-    results.push(...Search.performTermsSearch(searchTerms, excludedTerms));
+    normalResults.push(...Search.performTermsSearch(searchTerms, excludedTerms));
 
     // let the scorer override scores with a custom scoring function
-    if (Scorer.score) results.forEach((item) => (item[4] = Scorer.score(item)));
-
-    // now sort the results by score (in opposite order of appearance, since the
-    // display function below uses pop() to retrieve items) and then
-    // alphabetically
-    results.sort((a, b) => {
-      const leftScore = a[4];
-      const rightScore = b[4];
-      if (leftScore === rightScore) {
-        // same score: sort alphabetically
-        const leftTitle = a[1].toLowerCase();
-        const rightTitle = b[1].toLowerCase();
-        if (leftTitle === rightTitle) return 0;
-        return leftTitle > rightTitle ? -1 : 1; // inverted is intentional
-      }
-      return leftScore > rightScore ? 1 : -1;
-    });
+    if (Scorer.score) {
+      normalResults.forEach((item) => (item[4] = Scorer.score(item)));
+      nonMainIndexResults.forEach((item) => (item[4] = Scorer.score(item)));
+    }
+
+    // Sort each group of results by score and then alphabetically by name.
+    normalResults.sort(_orderResultsByScoreThenName);
+    nonMainIndexResults.sort(_orderResultsByScoreThenName);
+
+    // Combine the result groups in (reverse) order.
+    // Non-main index entries are typically arbitrary cross-references,
+    // so display them after other results.
+    let results = [...nonMainIndexResults, ...normalResults];
 
     // remove duplicate search results
     // note the reversing of results, so that in the case of duplicates, the highest-scoring entry is kept
@@ -361,7 +399,12 @@ const Search = {
       return acc;
     }, []);
 
-    results = results.reverse();
+    return results.reverse();
+  },
+
+  query: (query) => {
+    const [searchQuery, searchTerms, excludedTerms, highlightTerms, objectTerms] = Search._parseQuery(query);
+    const results = Search._performSearch(searchQuery, searchTerms, excludedTerms, highlightTerms, objectTerms);
 
     // for debugging
     //Search.lastresults = results.slice();  // a copy
@@ -466,14 +509,18 @@ const Search = {
       // add support for partial matches
       if (word.length > 2) {
         const escapedWord = _escapeRegExp(word);
-        Object.keys(terms).forEach((term) => {
-          if (term.match(escapedWord) && !terms[word])
-            arr.push({ files: terms[term], score: Scorer.partialTerm });
-        });
-        Object.keys(titleTerms).forEach((term) => {
-          if (term.match(escapedWord) && !titleTerms[word])
-            arr.push({ files: titleTerms[word], score: Scorer.partialTitle });
-        });
+        if (!terms.hasOwnProperty(word)) {
+          Object.keys(terms).forEach((term) => {
+            if (term.match(escapedWord))
+              arr.push({ files: terms[term], score: Scorer.partialTerm });
+          });
+        }
+        if (!titleTerms.hasOwnProperty(word)) {
+          Object.keys(titleTerms).forEach((term) => {
+            if (term.match(escapedWord))
+              arr.push({ files: titleTerms[term], score: Scorer.partialTitle });
+          });
+        }
       }
 
       // no match but word was a required one
@@ -496,9 +543,8 @@ const Search = {
 
       // create the mapping
       files.forEach((file) => {
-        if (fileMap.has(file) && fileMap.get(file).indexOf(word) === -1)
-          fileMap.get(file).push(word);
-        else fileMap.set(file, [word]);
+        if (!fileMap.has(file)) fileMap.set(file, [word]);
+        else if (fileMap.get(file).indexOf(word) === -1) fileMap.get(file).push(word);
       });
     });
 
@@ -549,8 +595,8 @@ const Search = {
    * search summary for a given text. keywords is a list
    * of stemmed words.
    */
-  makeSearchSummary: (htmlText, keywords) => {
-    const text = Search.htmlToText(htmlText);
+  makeSearchSummary: (htmlText, keywords, anchor) => {
+    const text = Search.htmlToText(htmlText, anchor);
     if (text === "") return null;
 
     const textLower = text.toLowerCase();

docs/_build/html/_static/language_data.js

@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>Index &mdash; pyreadstat 1.2.7 documentation</title>
+  <title>Index &mdash; pyreadstat 1.2.8 documentation</title>
       <link rel="stylesheet" type="text/css" href="_static/pygments.css?v=fa44fd50" />
       <link rel="stylesheet" type="text/css" href="_static/css/theme.css?v=19f00094" />
 
@@ -12,8 +12,8 @@
     <script src="_static/js/html5shiv.min.js"></script>
   <![endif]-->
 
-        <script src="_static/documentation_options.js?v=a5753347"></script>
-        <script src="_static/doctools.js?v=888ff710"></script>
+        <script src="_static/documentation_options.js?v=4d6f9085"></script>
+        <script src="_static/doctools.js?v=9a2dae69"></script>
         <script src="_static/sphinx_highlight.js?v=dc90522c"></script>
     <script src="_static/js/theme.js"></script>
     <link rel="index" title="Index" href="#" />