add pdf conversion doc and add docs.yml file

.github/workflows/docs.yml

@@ -0,0 +1,74 @@
+---
+name: Docs 📚
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - "_pkgdown.y[a]ml"
+      - DESCRIPTION
+      - "**.md"
+      - "**.Rmd"
+      - "man/**"
+      - "LICENSE.*"
+      - NAMESPACE
+      - "_quarto.yml"
+      - "index.qmd"
+  pull_request:
+    types:
+      - opened
+      - synchronize
+      - reopened
+      - ready_for_review
+    branches:
+      - main
+    paths:
+      - "_pkgdown.y[a]ml"
+      - DESCRIPTION
+      - "**.md"
+      - "**.Rmd"
+      - "man/**"
+      - "LICENSE.*"
+      - NAMESPACE
+      - "_quarto.yml"
+      - "index.qmd"
+  workflow_dispatch:
+
+jobs:
+  docs:
+    name: Quarto Docs 📕
+    runs-on: ubuntu-latest
+    container:
+      image: rocker/verse:4.4.0
+    permissions:
+      contents: write
+    steps:
+      - name: Check out repository 🛎️
+        uses: actions/checkout@v4.1.1
+
+      - name: Restore packages
+        shell: Rscript {0}
+        run: |
+          if (!requireNamespace("renv", quietly = TRUE)) install.packages("renv")
+          renv::install(c("rmarkdown", "yaml"))
+          renv::restore()
+
+      - name: Render Quarto Project 📑
+        run: quarto render --output-dir _site
+        shell: bash
+
+      - name: Upload Docs ⬆️
+        if: github.event_name != 'push'
+        uses: actions/upload-artifact@v4
+        with:
+          name: site
+          path: ./_site
+
+      - name: Publish Site 🗺️
+        if: github.event_name != 'pull_request'
+        uses: peaceiris/actions-gh-pages@v3
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          publish_dir: ./_site
+          destination_dir: "."

02_indentation.qmd

@@ -6,7 +6,7 @@ editor: visual
 
 The example table evaluates Indentation.
 
-```{r}
+```{r, eval=FALSE}
 library(gtsummary)
 tbl <- gtsummary::tbl_summary(gtsummary::trial, by = trt, include = c(age, grade), missing = "always", label = list(age = "Age")) |> add_overall()
 
@@ -64,13 +64,13 @@ doconv::docx2pdf("outputs/docx/indentation_gt_word.docx")
 
 ###### Preview the Output
 
-![](outputs/docx/indentation_gt_word.docx){width="80%" height="1000"}
+![](outputs/docx/indentation_gt_word.pdf){width="80%" height="1000"}
 
 |     | Date       | Finding                              |
 |-----|------------|--------------------------------------|
 | 1   | 06/19/2025 | cell contents replaced with xml code |
 
-```{html}
+```{html, eval= FALSE}
 # <md_container><w:p><w:pPr></w:pPr><w:r><w:rPr></w:rPr><w:t xml:space="preserve">Unknown</w:t></w:r></w:p></md_container>
 ```
 
@@ -84,6 +84,8 @@ doconv::docx2pdf("outputs/docx/indentation_qmd_word.docx")
 
 ###### Preview the Output
 
+![](outputs/docx/indentation_qmd_word.pdf){width="80%" height="1000"}
+
 |     | Date       | Finding                |
 |-----|------------|------------------------|
 | 1   | 06/19/2025 | No indentation applied |

03_spanning_header.qmd

@@ -4,7 +4,7 @@ format: html
 editor: visual
 ---
 
-```{r}
+```{r, eval=FALSE}
 library(gtsummary)
 
 tbl <- gtsummary::tbl_summary(gtsummary::trial, by = trt, include = c(age, grade), missing = "always", label = list(age = "Age")) |> add_overall()

04_footnotes.qmd

@@ -4,7 +4,7 @@ format: html
 editor: visual
 ---
 
-```{r}
+```{r, eval=FALSE}
 library(gtsummary)
 
 tbl <- gtsummary::tbl_summary(gtsummary::trial, by = trt, include = c(age, grade), missing = "always", label = list(age = "Age")) |> add_overall()

05_source_notes.qmd

@@ -4,7 +4,7 @@ format: html
 editor: visual
 ---
 
-```{r}
+```{r, eval=FALSE}
 library(gtsummary)
 
 tbl <- gtsummary::tbl_summary(gtsummary::trial, by = trt, include = c(age, grade), missing = "always", label = list(age = "Age")) |> add_overall()

06_titles.qmd

@@ -4,7 +4,7 @@ format: html
 editor: visual
 ---
 
-```{r}
+```{r, eval=FALSE}
 library(gtsummary)
 
 tbl <- gtsummary::tbl_summary(gtsummary::trial, by = trt, include = c(age, grade), missing = "always", label = list(age = "Age")) |> add_overall()

13_pdf_conversion.qmd

@@ -0,0 +1,81 @@
+---
+title: "PDF Conversion Outputs"
+format: html
+editor: visual
+---
+
+## docx to PDF Conversion
+
+There are limited opensource document converters available for converting tables in docx files to pdf output with high fidelity. One software explored is libreoffice. Findings from experimenting with this package:
+
+```{r, eval=FALSE}
+library(gtsummary)
+library(dplyr)
+
+set.seed(123)
+data <- dplyr::tibble(
+  id = 1:100,
+  age = sample(18:90, 100, replace = TRUE),
+  sex = sample(c("Male", "Female"), 100, replace = TRUE),
+  race = sample(c("White", "Black", "Asian", "Hispanic"), 100, replace = TRUE),
+  bmi = round(runif(100, 18, 35), 1),
+  smoking_status = sample(c("Never", "Former", "Current"), 100, replace = TRUE),
+  diabetes = sample(c("Yes", "No"), 100, replace = TRUE),
+  hypertension = sample(c("Yes", "No"), 100, replace = TRUE),
+  heart_disease = sample(c("Yes", "No"), 100, replace = TRUE),
+  cancer = sample(c("Yes", "No"), 100, replace = TRUE),
+  cholesterol = sample(c("Normal", "High"), 100, replace = TRUE),
+  exercise_frequency = sample(0:7, 100, replace = TRUE),
+  alcohol_intake = sample(c("None", "Low", "Moderate", "High"), 100, replace = TRUE),
+  family_history = sample(c("Yes", "No"), 100, replace = TRUE),
+  education = sample(c("High School", "College", "Graduate"), 100, replace = TRUE),
+  marital_status = sample(c("Single", "Married", "Divorced"), 100, replace = TRUE),
+  employment_status = sample(c("Employed", "Unemployed", "Retired"), 100, replace = TRUE),
+  region = sample(c("North", "South", "East", "West"), 100, replace = TRUE),
+  health_insurance = sample(c("Yes", "No"), 100, replace = TRUE),
+  medication = sample(c("Yes", "No"), 100, replace = TRUE),
+  visits_last_year = sample(0:10, 100, replace = TRUE),
+  satisfaction = sample(1:5, 100, replace = TRUE)
+)
+
+# Create summary table
+summary_table <- data %>%
+  tbl_summary(
+    by = sex,  # Group by sex
+    statistic = list(all_continuous() ~ "{mean} ({sd})", all_categorical() ~ "{n} ({p}%)"),
+    label = list(
+      age ~ "Age (years)",
+      bmi ~ "BMI",
+      smoking_status ~ "Smoking Status",
+      diabetes ~ "Diabetes",
+      hypertension ~ "Hypertension",
+      heart_disease ~ "Heart Disease",
+      cancer ~ "Cancer",
+      cholesterol ~ "Cholesterol",
+      exercise_frequency ~ "Exercise Frequency (days/week)",
+      alcohol_intake ~ "Alcohol Intake",
+      family_history ~ "Family History",
+      education ~ "Education Level",
+      marital_status ~ "Marital Status",
+      employment_status ~ "Employment Status",
+      region ~ "Region",
+      health_insurance ~ "Health Insurance",
+      medication ~ "On Medication",
+      visits_last_year ~ "Visits Last Year",
+      satisfaction ~ "Health Satisfaction (1-5)"
+    )
+  ) %>%
+  add_n() %>%
+  modify_header(label = "**Characteristic**", estimate = "**Mean (SD) or N (%)**") %>%
+  modify_table_styling(columns = everything())
+
+# save as a word document
+gt::gtsave(as_gt(summary_table), filename = "outputs/docx/too_long_libreoffice_word.docx")
+
+```
+
+Convert the word document to pdf using libreoffice
+
+```{bash, eval = FALSE}
+# soffice --headless --convert-to pdf "outputs/docx/too_long_libreoffice_word.docx" --outdir "outputs/pdf"
+```

_quarto.yml

@@ -39,7 +39,7 @@ knitr:
 website:
   page-navigation: true
   title: "Table Drawing Research"
-  description: "Table Engine output Experimentation"
+  description: "Table Engine Output Experimentation"
 
   repo-url: https://github.com/insightsengineering/table.drawing.research
   repo-actions: [edit, issue]
@@ -80,4 +80,6 @@ website:
        text: Table Too Wide
      - href: 11_other_engines.qmd
        text: Other Engines
+     - href: 13_pdf_conversion.qmd
+       text: PDF Conversion
 editor: source