Package v0.9.8 cran release

Author: MarcusKlik

.Rbuildignore

@@ -1,3 +1,4 @@
+^\.github$
 ^.*\.Rproj$
 ^\.Rproj\.user$
 \.o$
@@ -19,3 +20,4 @@ LZ4/LICENSE$
 ^CRAN-RELEASE$
 ^revdep$
 ^\.github$
+^CRAN-SUBMISSION$

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

@@ -1,10 +1,12 @@
-# Workflow derived from https://github.com/r-lib/actions/tree/master/examples
+# Workflow derived from https://github.com/r-lib/actions/tree/v2/examples
 # Need help debugging build failures? Start at https://github.com/r-lib/actions#where-to-find-help
+#
+# NOTE: This workflow is overkill for most R packages and
+# check-standard.yaml is likely a better choice.
+# usethis::use_github_action("check-standard") will install it.
 on:
   push:
-    branches: [develop, release, hotfix, master]
   pull_request:
-    branches: [develop, release, hotfix, master]
 
 name: R-CMD-check
 
@@ -19,10 +21,12 @@ jobs:
       matrix:
         config:
           - {os: macOS-latest,   r: 'release'}
-          - {os: windows-latest, r: 'release'}
-          - {os: ubuntu-latest,   r: 'devel', http-user-agent: 'release'}
-          - {os: ubuntu-latest,   r: 'release'}
-          - {os: ubuntu-latest,   r: 'oldrel-1'}
+          - {os: windows-2022,   r: 'devel'}
+          - {os: windows-latest, r: '4.1'}
+          - {os: windows-latest, r: '3.6'}
+          - {os: ubuntu-20.04,    r: 'devel', http-user-agent: 'release'}
+          - {os: ubuntu-20.04,   r: 'release'}
+          - {os: ubuntu-18.04,   r: 'oldrel-4'}
 
     env:
       GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
@@ -31,28 +35,17 @@ jobs:
     steps:
       - uses: actions/checkout@v2
 
-      - uses: r-lib/actions/setup-pandoc@v1
+      - uses: r-lib/actions/setup-pandoc@v2
 
-      - uses: r-lib/actions/setup-r@v1
+      - uses: r-lib/actions/setup-r@v2
         with:
           r-version: ${{ matrix.config.r }}
           http-user-agent: ${{ matrix.config.http-user-agent }}
           use-public-rspm: true
 
-      - uses: r-lib/actions/setup-r-dependencies@v1
+      - uses: r-lib/actions/setup-r-dependencies@v2
         with:
-          extra-packages: rcmdcheck
+          extra-packages: any::rcmdcheck
+          needs: check
 
-      - uses: r-lib/actions/check-r-package@v1
-
-      - name: Show testthat output
-        if: always()
-        run: find check -name 'testthat.Rout*' -exec cat '{}' \; || true
-        shell: bash
-
-      - name: Upload check results
-        if: failure()
-        uses: actions/upload-artifact@main
-        with:
-          name: ${{ runner.os }}-r${{ matrix.config.r }}-results
-          path: check
+      - uses: r-lib/actions/check-r-package@v2

.travis.yml

@@ -1,26 +1,129 @@
 
-# Contributor Code of Conduct
+# Contributor Covenant Code of Conduct
 
-As contributors and maintainers of this project, we pledge to respect all people who 
-contribute through reporting issues, posting feature requests, updating documentation,
-submitting pull requests or patches, and other activities.
+## Our Pledge
 
-We are committed to making participation in this project a harassment-free experience for
-everyone, regardless of level of experience, gender, gender identity and expression,
-sexual orientation, disability, personal appearance, body size, race, ethnicity, age, or religion.
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, religion, or sexual identity
+and orientation.
 
-Examples of unacceptable behavior by participants include the use of sexual language or
-imagery, derogatory comments or personal attacks, trolling, public or private harassment,
-insults, or other unprofessional conduct.
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
 
-Project maintainers have the right and responsibility to remove, edit, or reject comments,
-commits, code, wiki edits, issues, and other contributions that are not aligned to this 
-Code of Conduct. Project maintainers who do not follow the Code of Conduct may be removed 
-from the project team.
+## Our Standards
 
-Instances of abusive, harassing, or otherwise unacceptable behavior may be reported by 
-opening an issue or contacting one or more of the project maintainers.
+Examples of behavior that contributes to a positive environment for our
+community include:
 
-This Code of Conduct is adapted from the Contributor Covenant 
-(http://contributor-covenant.org), version 1.0.0, available at 
-http://contributor-covenant.org/version/1/0/0/
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the
+  overall community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or
+  advances of any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email
+  address, without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official e-mail address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the community leaders responsible for enforcement at
+[INSERT CONTACT METHOD].
+All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the
+reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series
+of actions.
+
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or
+permanent ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior,  harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within
+the community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.0, available at
+https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
+
+Community Impact Guidelines were inspired by [Mozilla's code of conduct
+enforcement ladder](https://github.com/mozilla/diversity).
+
+[homepage]: https://www.contributor-covenant.org
+
+For answers to common questions about this code of conduct, see the FAQ at
+https://www.contributor-covenant.org/faq. Translations are available at
+https://www.contributor-covenant.org/translations.

CONDUCT.md

@@ -1,22 +1,21 @@
 Package: fst
 Type: Package
 Title: Lightning Fast Serialization of Data Frames
-Description: Multithreaded serialization of compressed data frames using the
-    'fst' format. The 'fst' format allows for random access of stored data and
-    compression with the LZ4 and ZSTD compressors created by Yann Collet. The ZSTD
-    compression library is owned by Facebook Inc.
-Version: 0.9.6
-Date: 2022-02-01
-Authors@R: c(
-    person("Mark", "Klik", email = "[email protected]", role = c("aut", "cre", "cph")),
-    person("Yann", "Collet", role = c("ctb", "cph"),
-      comment = "Yann Collet is author of the bundled LZ4 and ZSTD code and copyright holder of LZ4"),
-    person("Facebook, Inc.", role = "cph", comment = "Bundled ZSTD code"))
+Description: Multithreaded serialization of compressed data frames using the 'fst' format. The
+    'fst' format allows for full random access of stored data and a wide range of compression
+    settings using the LZ4 and ZSTD compressors.
+Version: 0.9.8
+Date: 2022-02-07
+Authors@R:
+    person("Mark", "Klik", email = "[email protected]", role = c("aut", "cre", "cph"))
 Depends:
     R (>= 3.0.0)
 Imports:
+    fstcore,
     Rcpp
-LinkingTo: Rcpp
+LinkingTo:
+    Rcpp,
+    fstcore
 SystemRequirements: little-endian platform
 RoxygenNote: 7.1.2
 Suggests:
@@ -28,8 +27,5 @@ Suggests:
     crayon
 License: AGPL-3 | file LICENSE
 Encoding: UTF-8
-Copyright: This package includes sources from the LZ4 library written
-    by Yann Collet, sources of the ZSTD library owned by Facebook, Inc.
-    and sources of the fstlib library owned by Mark Klik
 URL: http://www.fstpackage.org
 BugReports: https://github.com/fstpackage/fst/issues

DESCRIPTION

@@ -23,7 +23,8 @@ export(read_fst)
 export(threads_fst)
 export(write.fst)
 export(write_fst)
-importFrom(Rcpp,sourceCpp)
+import(Rcpp)
+importFrom(fstcore,threads_fstlib)
 importFrom(parallel,detectCores)
 importFrom(utils,capture.output)
 importFrom(utils,packageVersion)

NAMESPACE

@@ -1,4 +1,22 @@
 
+# fst 0.9.8
+
+With this release of `fst`, the `fstlib` library is no longer build with the `fst` package, but
+imported from package `fstcore`. This allows for better separation of updates of the C++ code underlying the `fst`
+format and the R wrapper package. Also, with this setup, other packages can directly use the C++ interface exported
+from the fstcore package.
+
+## Bugs solved
+
+* The package had linking problems on ARM macOS systems, preventing a correct build. These problems originated from
+minor differences between the xxHash implementations in the LZ4 and ZSTD libraries and incorrect linker parameters.
+
+## Library updates
+
+* Library LZ4 updated to version 1.9.3
+* library ZSTD updated to version 1.5.2
+
+
 # fst 0.9.6
 
 Version 0.9.6 is a minor update to 'hotfix' an issue with the use of `sample.int()`. All calls to `sample.int()` now

NEWS.md

@@ -1,10 +1,6 @@
 # Generated by using Rcpp::compileAttributes() -> do not edit by hand
 # Generator token: 10BE3573-1514-4C36-9D1C-5A225CD40393
 
-fstlib_version <- function() {
-    .Call(`_fst_fstlib_version`)
-}
-
 fststore <- function(fileName, table, compression, uniformEncoding) {
     .Call(`_fst_fststore`, fileName, table, compression, uniformEncoding)
 }
@@ -37,11 +33,11 @@ setnrofthreads <- function(nrOfThreads) {
     .Call(`_fst_setnrofthreads`, nrOfThreads)
 }
 
-hasopenmp <- function() {
-    .Call(`_fst_hasopenmp`)
-}
-
 restore_after_fork <- function(restore) {
     invisible(.Call(`_fst_restore_after_fork`, restore))
 }
 
+hasopenmp <- function() {
+    .Call(`_fst_hasopenmp`)
+}
+

R/RcppExports.R

@@ -218,11 +218,15 @@ read_fst <- function(path, columns = NULL, from = 1, to = NULL, as.data.table =
     stop(res)
   }
 
+  nr_of_rows <- 0
+  if (length(res$resTable) > 0) {  # check for NULL tables's
+    nr_of_rows <- length(res$resTable[[1]])
+  }
+
   # long vectors are not supported yet with data.table, tibble's or data.frame,
   # so return a list instead
-  nr_of_rows <- length(res$resTable[[1]])
   if (nr_of_rows >= 2 ^ 31) {
-    return(res$resTable)
+      return(res$resTable)
   }
 
   if (as.data.table) {
@@ -241,10 +245,10 @@ read_fst <- function(path, columns = NULL, from = 1, to = NULL, as.data.table =
   # use setters from data.table to improve performance
   if (requireNamespace("data.table", quietly = TRUE)) {
     data.table::setattr(res_table, "class", "data.frame")
-    data.table::setattr(res_table, "row.names", seq_len(length(res_table[[1L]])))
+    data.table::setattr(res_table, "row.names", base::.set_row_names(nr_of_rows))
   } else {
     class(res_table) <- "data.frame"
-    attr(res_table, "row.names") <- seq_len(length(res_table[[1L]]))
+    attr(res_table, "row.names") <- base::.set_row_names(nr_of_rows)
   }
 
   res_table