Update from dev branch of readstat

.github/workflows/R-CMD-check.yaml

@@ -8,9 +8,10 @@ on:
   push:
     branches: [main, master]
   pull_request:
-    branches: [main, master]
 
-name: R-CMD-check
+name: R-CMD-check.yaml
+
+permissions: read-all
 
 jobs:
   R-CMD-check:
@@ -25,24 +26,22 @@ jobs:
           - {os: macos-latest,   r: 'release'}
 
           - {os: windows-latest, r: 'release'}
-          # Use 3.6 to trigger usage of RTools35
-          - {os: windows-latest, r: '3.6'}
-          # use 4.1 to check with rtools40's older compiler
-          - {os: windows-latest, r: '4.1'}
-
-          - {os: ubuntu-latest,   r: 'devel', http-user-agent: 'release'}
-          - {os: ubuntu-latest,   r: 'release'}
-          - {os: ubuntu-latest,   r: 'oldrel-1'}
-          - {os: ubuntu-latest,   r: 'oldrel-2'}
-          - {os: ubuntu-latest,   r: 'oldrel-3'}
-          - {os: ubuntu-latest,   r: 'oldrel-4'}
+          # use 4.0 or 4.1 to check with rtools40's older compiler
+          - {os: windows-latest, r: 'oldrel-4'}
+
+          - {os: ubuntu-latest,  r: 'devel', http-user-agent: 'release'}
+          - {os: ubuntu-latest,  r: 'release'}
+          - {os: ubuntu-latest,  r: 'oldrel-1'}
+          - {os: ubuntu-latest,  r: 'oldrel-2'}
+          - {os: ubuntu-latest,  r: 'oldrel-3'}
+          - {os: ubuntu-latest,  r: 'oldrel-4'}
 
     env:
       GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
       R_KEEP_PKG_SOURCE: yes
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - uses: r-lib/actions/setup-pandoc@v2
 
@@ -60,3 +59,4 @@ jobs:
       - uses: r-lib/actions/check-r-package@v2
         with:
           upload-snapshots: true
+          build_args: 'c("--no-manual","--compact-vignettes=gs+qpdf")'

.github/workflows/pkgdown.yaml

@@ -4,12 +4,13 @@ on:
   push:
     branches: [main, master]
   pull_request:
-    branches: [main, master]
   release:
     types: [published]
   workflow_dispatch:
 
-name: pkgdown
+name: pkgdown.yaml
+
+permissions: read-all
 
 jobs:
   pkgdown:
@@ -22,7 +23,7 @@ jobs:
     permissions:
       contents: write
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - uses: r-lib/actions/setup-pandoc@v2
 
@@ -41,7 +42,7 @@ jobs:
 
       - name: Deploy to GitHub pages 🚀
         if: github.event_name != 'pull_request'
-        uses: JamesIves/github-pages-deploy-action@v4.4.1
+        uses: JamesIves/github-pages-deploy-action@v4.5.0
         with:
           clean: false
           branch: gh-pages

.github/workflows/pr-commands.yaml

@@ -4,7 +4,9 @@ on:
   issue_comment:
     types: [created]
 
-name: Commands
+name: pr-commands.yaml
+
+permissions: read-all
 
 jobs:
   document:
@@ -13,8 +15,10 @@ jobs:
     runs-on: ubuntu-latest
     env:
       GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+    permissions:
+      contents: write
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - uses: r-lib/actions/pr-fetch@v2
         with:
@@ -50,8 +54,10 @@ jobs:
     runs-on: ubuntu-latest
     env:
       GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+    permissions:
+      contents: write
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - uses: r-lib/actions/pr-fetch@v2
         with:

.github/workflows/test-coverage.yaml

@@ -4,9 +4,10 @@ on:
   push:
     branches: [main, master]
   pull_request:
-    branches: [main, master]
 
-name: test-coverage
+name: test-coverage.yaml
+
+permissions: read-all
 
 jobs:
   test-coverage:
@@ -15,36 +16,47 @@ jobs:
       GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - uses: r-lib/actions/setup-r@v2
         with:
           use-public-rspm: true
 
       - uses: r-lib/actions/setup-r-dependencies@v2
         with:
-          extra-packages: any::covr
+          extra-packages: any::covr, any::xml2
           needs: coverage
 
       - name: Test coverage
         run: |
-          covr::codecov(
+          cov <- covr::package_coverage(
             quiet = FALSE,
             clean = FALSE,
             install_path = file.path(normalizePath(Sys.getenv("RUNNER_TEMP"), winslash = "/"), "package")
           )
+          print(cov)
+          covr::to_cobertura(cov)
         shell: Rscript {0}
 
+      - uses: codecov/codecov-action@v5
+        with:
+          # Fail if error if not on PR, or if on PR and token is given
+          fail_ci_if_error: ${{ github.event_name != 'pull_request' || secrets.CODECOV_TOKEN }}
+          files: ./cobertura.xml
+          plugins: noop
+          disable_search: true
+          token: ${{ secrets.CODECOV_TOKEN }}
+
       - name: Show testthat output
         if: always()
         run: |
           ## --------------------------------------------------------------------
-          find ${{ runner.temp }}/package -name 'testthat.Rout*' -exec cat '{}' \; || true
+          find '${{ runner.temp }}/package' -name 'testthat.Rout*' -exec cat '{}' \; || true
         shell: bash
 
       - name: Upload test results
         if: failure()
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
           name: coverage-test-failures
           path: ${{ runner.temp }}/package

README.Rmd

@@ -18,7 +18,7 @@ knitr::opts_chunk$set(
 <!-- badges: start -->
 [![CRAN status](https://www.r-pkg.org/badges/version/haven)](https://cran.r-project.org/package=haven)
 [![R-CMD-check](https://github.com/tidyverse/haven/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/tidyverse/haven/actions/workflows/R-CMD-check.yaml)
-[![Codecov test coverage](https://codecov.io/gh/tidyverse/haven/branch/main/graph/badge.svg)](https://app.codecov.io/gh/tidyverse/haven?branch=main)
+[![Codecov test coverage](https://codecov.io/gh/tidyverse/haven/graph/badge.svg)](https://app.codecov.io/gh/tidyverse/haven)
 <!-- badges: end -->
 
 ## Overview

README.md

@@ -9,7 +9,7 @@
 status](https://www.r-pkg.org/badges/version/haven)](https://cran.r-project.org/package=haven)
 [![R-CMD-check](https://github.com/tidyverse/haven/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/tidyverse/haven/actions/workflows/R-CMD-check.yaml)
 [![Codecov test
-coverage](https://codecov.io/gh/tidyverse/haven/branch/main/graph/badge.svg)](https://app.codecov.io/gh/tidyverse/haven?branch=main)
+coverage](https://codecov.io/gh/tidyverse/haven/graph/badge.svg)](https://app.codecov.io/gh/tidyverse/haven)
 <!-- badges: end -->
 
 ## Overview

src/cpp11.cpp

@@ -110,9 +110,9 @@ extern "C" SEXP _haven_write_xpt_(SEXP data, SEXP path, SEXP version, SEXP name,
 
 extern "C" {
 /* .Call calls */
-extern SEXP is_tagged_na_(void *, void *);
-extern SEXP na_tag_(void *);
-extern SEXP tagged_na_(void *);
+extern SEXP is_tagged_na_(SEXP, SEXP);
+extern SEXP na_tag_(SEXP);
+extern SEXP tagged_na_(SEXP);
 
 static const R_CallMethodDef CallEntries[] = {
     {"_haven_df_parse_dta_file", (DL_FUNC) &_haven_df_parse_dta_file, 6},

src/readstat/readstat.h

@@ -104,11 +104,22 @@ typedef enum readstat_error_e {
     READSTAT_ERROR_TOO_FEW_COLUMNS,
     READSTAT_ERROR_TOO_MANY_COLUMNS,
     READSTAT_ERROR_NAME_IS_ZERO_LENGTH,
-    READSTAT_ERROR_BAD_TIMESTAMP_VALUE
+    READSTAT_ERROR_BAD_TIMESTAMP_VALUE,
+    READSTAT_ERROR_BAD_MR_STRING
 } readstat_error_t;
 
 const char *readstat_error_message(readstat_error_t error_code);
 
+typedef struct mr_set_s {
+    char   type;
+    char  *name;
+    char  *label;
+    int    is_dichotomy;
+    int    counted_value;
+    char **subvariables;
+    int    num_subvars;
+} mr_set_t;
+
 typedef struct readstat_metadata_s {
     int64_t     row_count;
     int64_t     var_count;
@@ -121,6 +132,8 @@ typedef struct readstat_metadata_s {
     const char *file_label;
     const char *file_encoding;
     unsigned int is64bit:1;
+    size_t multiple_response_sets_length;
+    mr_set_t *mr_sets;
 } readstat_metadata_t;
 
 /* If the row count is unknown (e.g. it's an XPORT or POR file, or an SAV
@@ -138,6 +151,8 @@ readstat_endian_t readstat_get_endianness(readstat_metadata_t *metadata);
 const char *readstat_get_table_name(readstat_metadata_t *metadata);
 const char *readstat_get_file_label(readstat_metadata_t *metadata);
 const char *readstat_get_file_encoding(readstat_metadata_t *metadata);
+const mr_set_t *readstat_get_multiple_response_sets(readstat_metadata_t *metadata);
+size_t readstat_get_multiple_response_sets_length(readstat_metadata_t *metadata);
 
 typedef struct readstat_value_s {
     union {

src/readstat/readstat_metadata.c

@@ -43,3 +43,11 @@ const char *readstat_get_file_encoding(readstat_metadata_t *metadata) {
 const char *readstat_get_table_name(readstat_metadata_t *metadata) {
     return metadata->table_name;
 }
+
+size_t readstat_get_multiple_response_sets_length(readstat_metadata_t *metadata) {
+    return metadata->multiple_response_sets_length;
+}
+
+const mr_set_t *readstat_get_multiple_response_sets(readstat_metadata_t *metadata) {
+    return metadata->mr_sets;
+}

src/readstat/sas/ieee.c

@@ -366,7 +366,7 @@ void ieee2xpt(unsigned char *ieee, unsigned char *xport) {
     shift = (int)
         (ieee_exp = (int)(((ieee1 >> 16) & 0x7ff0) >> 4) - 1023)
         & 3;
-    /* the ieee format has an implied "1" immdeiately to the left */
+    /* the ieee format has an implied "1" immediately to the left */
     /* of the binary point. Show it in here. */
     xport1 |= 0x00100000;
     if (shift)
@@ -377,7 +377,7 @@ void ieee2xpt(unsigned char *ieee, unsigned char *xport) {
         /* from the lower half that would have been shifted in (if */
         /* we could shift a double). The shift count can never */
         /* exceed 3, so all we care about are the high order 3 */
-        /* bits. We don't want sign extention so make sure it's an */
+        /* bits. We don't want sign extension so make sure it's an */
         /* unsigned char. We'll shift either5, 6, or 7 places to */
         /* keep 3, 2, or 1 bits. After that, shift the second half */
         /* of the number the right number of places. We always get */
@@ -391,9 +391,9 @@ void ieee2xpt(unsigned char *ieee, unsigned char *xport) {
 
     /* Now set the ibm exponent and the sign of the fraction. The */
     /* power of 2 ieee exponent must be divided by 4 and made */
-    /* excess 64 (we add 65 here because of the poisition of the */
+    /* excess 64 (we add 65 here because of the position of the */
     /* fraction bits, essentially 4 positions lower than they */
-    /* should be so we incrment the ibm exponent). */
+    /* should be so we increment the ibm exponent). */
 
     xport1 |=
 

src/readstat/sas/readstat_sas.c

@@ -124,7 +124,8 @@ static time_t sas_epoch(void) {
     return - 3653 * 86400; // seconds between 01-01-1960 and 01-01-1970
 }
 
-static time_t sas_convert_time(double time, time_t epoch) {
+static time_t sas_convert_time(double time, double time_diff, time_t epoch) {
+    time -= time_diff;
     time += epoch;
     if (isnan(time))
         return 0;
@@ -212,7 +213,7 @@ readstat_error_t sas_read_header(readstat_io_t *io, sas_header_info_t *hinfo,
         goto cleanup;
     }
 
-    double creation_time, modification_time;
+    double creation_time, modification_time, creation_time_diff, modification_time_diff;
 
     if (io->read(&creation_time, sizeof(double), io->io_ctx) < sizeof(double)) {
         retval = READSTAT_ERROR_READ;
@@ -228,13 +229,22 @@ readstat_error_t sas_read_header(readstat_io_t *io, sas_header_info_t *hinfo,
     if (bswap)
         modification_time = byteswap_double(modification_time);
 
-    hinfo->creation_time = sas_convert_time(creation_time, epoch);
-    hinfo->modification_time = sas_convert_time(modification_time, epoch);
-
-    if (io->seek(16, READSTAT_SEEK_CUR, io->io_ctx) == -1) {
-        retval = READSTAT_ERROR_SEEK;
+    if (io->read(&creation_time_diff, sizeof(double), io->io_ctx) < sizeof(double)) {
+        retval = READSTAT_ERROR_READ;
         goto cleanup;
     }
+    if (bswap)
+        creation_time_diff = byteswap_double(creation_time_diff);
+
+    if (io->read(&modification_time_diff, sizeof(double), io->io_ctx) < sizeof(double)) {
+        retval = READSTAT_ERROR_READ;
+        goto cleanup;
+    }
+    if (bswap)
+        modification_time_diff = byteswap_double(modification_time_diff);
+
+    hinfo->creation_time = sas_convert_time(creation_time, creation_time_diff, epoch);
+    hinfo->modification_time = sas_convert_time(modification_time, modification_time_diff, epoch);
 
     uint32_t header_size, page_size;
 
@@ -299,9 +309,9 @@ readstat_error_t sas_read_header(readstat_io_t *io, sas_header_info_t *hinfo,
         retval = READSTAT_ERROR_READ;
         goto cleanup;
     }
-    char major;
+    char major, revision_tag;
     int minor, revision;
-    if (sscanf(header_end.release, "%c.%04dM%1d", &major, &minor, &revision) != 3) {
+    if (sscanf(header_end.release, "%c.%04d%c%1d", &major, &minor, &revision_tag, &revision) != 4) {
         retval = READSTAT_ERROR_PARSE;
         goto cleanup;
     }
@@ -316,6 +326,11 @@ readstat_error_t sas_read_header(readstat_io_t *io, sas_header_info_t *hinfo,
         retval = READSTAT_ERROR_PARSE;
         goto cleanup;
     }
+    // revision_tag is usually M, but J has been observed in the wild (not created with SAS?)
+    if (revision_tag != 'M' && revision_tag != 'J') {
+        retval = READSTAT_ERROR_PARSE;
+        goto cleanup;
+    }
     hinfo->minor_version = minor;
     hinfo->revision = revision;