Nomad changes

docs/snippets/r/getting-started/basic_extraction.md

@@ -0,0 +1,7 @@
+```r
+library(kreuzberg)
+
+# Extract text from a PDF file
+result <- extract_file_sync("document.pdf")
+cat(result$content)
+```

docs/snippets/r/getting-started/basic_usage.md

@@ -0,0 +1,15 @@
+```r title="R"
+library(kreuzberg)
+
+config <- ExtractionConfig$default()
+
+json <- extract_file_sync(
+  path = "document.pdf",
+  mime_type = NULL,
+  config = config
+)
+result <- jsonlite::fromJSON(json, simplifyVector = FALSE)
+
+cat(result$content)
+cat(sprintf("\nMIME Type: %s\n", result$mime_type))
+```

docs/snippets/r/getting-started/extract_file.md

@@ -0,0 +1,14 @@
+```r title="R"
+library(kreuzberg)
+
+# Extract a file and inspect the result
+result <- extract_file_sync("document.pdf")
+
+# Print result information
+cat(sprintf("MIME type: %s\n", mime_type(result)))
+cat(sprintf("Content length: %d characters\n", nchar(content(result))))
+cat(sprintf("Page count: %d\n", page_count(result)))
+
+# View additional metadata
+cat(sprintf("Detected language: %s\n", detected_language(result)))
+```

docs/snippets/r/getting-started/extract_with_ocr.md

@@ -0,0 +1,19 @@
+```r title="R"
+library(kreuzberg)
+
+# Configure OCR settings via a plain list mirroring the config JSON.
+config <- list(
+  force_ocr = TRUE,
+  ocr = list(
+    backend = "tesseract",
+    language = "eng"
+  )
+)
+
+# Extract an image file with OCR enabled
+json <- extract_file_sync("image.png", "image/png", config)
+result <- jsonlite::fromJSON(json, simplifyVector = FALSE)
+
+cat("Extracted text from image:\n")
+cat(result$content)
+```

docs/snippets/r/getting-started/hello_world.md

@@ -0,0 +1,12 @@
+```r title="R"
+library(kreuzberg)
+
+# Extract a PDF file
+result <- extract_file_sync("example.pdf")
+
+# Print a preview of the extracted content
+content_preview <- substr(content(result), 1L, 200L)
+cat("Content preview:\n")
+cat(content_preview)
+cat("\n...\n")
+```

docs/snippets/r/getting-started/install_verify.md

@@ -0,0 +1,7 @@
+```r title="R"
+library(kreuzberg)
+
+# Confirm the native extension loaded by listing registered extractors
+extractors <- list_document_extractors()
+cat(sprintf("kreuzberg ready: %d document extractors registered\n", length(extractors)))
+```

docs/snippets/r/getting-started/installation.md

@@ -0,0 +1,7 @@
+```r
+# Install from source (requires Rust toolchain)
+# install.packages("kreuzberg")
+
+# Or install from GitHub
+# remotes::install_github("kreuzberg-dev/kreuzberg", subdir = "packages/r")
+```

docs/snippets/r/getting-started/read_content.md

@@ -0,0 +1,20 @@
+```r title="R"
+library(kreuzberg)
+
+# Extract a document
+result <- extract_file_sync("document.docx")
+
+# Access core content fields
+cat(sprintf("MIME type: %s\n", mime_type(result)))
+cat(sprintf("Content length: %d characters\n", nchar(content(result))))
+
+# Access structured data
+cat(sprintf("Number of tables: %d\n", length(result$tables)))
+cat(sprintf("Detected language: %s\n", detected_language(result)))
+
+# Access metadata
+author <- metadata_field(result, "author")
+if (!is.null(author)) {
+  cat(sprintf("Document author: %s\n", author))
+}
+```