Merge pull request #17 from TidierOrg/add-gen_reader

Add gen reader
add reading rdata supprt

Project.toml

@@ -1,7 +1,7 @@
 name = "TidierFiles"
 uuid = "8ae5e7a9-bdd3-4c93-9cc3-9df4d5d947db"
 authors = ["Daniel Rizk <[email protected]> and contributors"]
-version = "0.1.3"
+version = "0.1.4"
 
 [deps]
 Arrow = "69666777-d1a9-59fb-9406-91d4454c9d45"
@@ -11,6 +11,7 @@ Dates = "ade2ca70-3891-5945-98fb-dc099432e06a"
 Documenter = "e30172f5-a6a5-5a46-863b-614d45cd2de4"
 HTTP = "cd3eb016-35fb-5094-929b-558a96fad6f3"
 Parquet2 = "98572fba-bba0-415d-956f-fa77e587d26d"
+RData = "df47a6cb-8c03-5eed-afd8-b6050d6c41da"
 ReadStatTables = "52522f7a-9570-4e34-8ac6-c005c74d4b84"
 Reexport = "189a3867-3050-52da-a836-e630ba90ab69"
 XLSX = "fdbf4ff8-1666-58a4-91e7-1b58723a45e0"
@@ -26,6 +27,7 @@ Parquet2 = "0.2"
 ReadStatTables = "0.3"
 Reexport = "0.2, 1"
 XLSX = "0.10"
+RData = "1.0"
 julia = "1.9"
 
 [extras]

README.md

@@ -24,6 +24,10 @@ Currently supported file types:
 - `read_dta` and `write_dta` (.dta) 
 - `read_arrow` and `write_arrow`
 - `read_parquet` and `write_parquet`
+- `read_rdata` (.rdata and .rds)
+
+Agnostic read and write functions that detect the type and dispatch the appropriate function. 
+- `read_file` and `write_file` 
 
 # Examples
 

docs/examples/UserGuide/r_files.jl

@@ -0,0 +1,15 @@
+# Reading .rds and .rdata files is made possible via RData.jl. There is currently no write support, nor is there url support.
+
+# To read the file, simply pass the path to `read_rdata` or `read_file`. There is a small difference between .rds and .rdata files. 
+# .rdata files will contain a dict of the table name and the data frame. There can be multiple entries in one .rdata file. To access the data frame, you must pass the name of the dict to the object.
+
+# ```julia
+# using TidierFiles 
+# file = read_rdata("path.rdata) # or read_file("path.rdata)
+# df = file["entry_name"]
+# ```
+
+# This is in contrast to .rds files which will contain one data frame.
+# ```julia
+# df = read_rdata("path.rds)
+# ```

docs/examples/UserGuide/xl.jl

@@ -23,4 +23,12 @@
 
 # - `x`: The data to write. Can be a single `Pair{String, DataFrame}` for writing one sheet, or a `Tuple` of such pairs for writing multiple sheets. The `String` in each pair specifies the sheet name, and the `DataFrame` is the data to write to that sheet.
 # - `path`: The path to the output Excel file.
-# - `overwrite`: Whether to overwrite an existing file. Default is `false`.
+# - `overwrite`: Whether to overwrite an existing file. Default is `false`.
+
+# ## Writing to a specific sheet
+# The example below demonstrates how to write to specific sheets in a file.
+# The string in the `Dict` is the sheet name, it can be new or preexisting. The second component is the dataframe to be written to that sheet.
+# In this example, two sheets, "REPORT_A" and "REPORT_C" are being written to with `df` and `df2` respectively.
+# ```julia
+# write_xlsx(("REPORT_A" => df, "REPORT_C" => df2); path = "/Users/danielrizk/Downloads/xlsxtest2.xlsx", overwrite = true)
+# ```

docs/mkdocs.yml

@@ -121,4 +121,5 @@ nav:
   - "Stats Files": "examples/generated/UserGuide/stats.md"
   - "Arrow Files": "examples/generated/UserGuide/Arrow.md"
   - "Parquet Files": "examples/generated/UserGuide/parquet.md"
+  - "R Data Files": "examples/generated/UserGuide/r_files.md"
   - "Reference" : "reference.md"

docs/src/index.md

@@ -21,6 +21,10 @@ Currently supported file types:
 - `read_dta` and `write_dta` (.dta) 
 - `read_arrow` and `write_arrow`
 - `read_parquet` and `write_parquet`
+- `read_rdata` (.rdata and .rds)
+
+Agnostic read and write functions that detect the type and dispatch the appropriate function. 
+- `read_file` and `write_file` 
 
 # Examples
 

src/TidierFiles.jl

@@ -9,12 +9,13 @@ using ReadStatTables
 using Reexport
 using Parquet2
 using Arrow
+using RData
 
 @reexport using DataFrames: DataFrame
 
 export read_csv, write_csv, read_tsv, write_tsv, read_table, write_table, read_delim, read_xlsx, write_xlsx, 
  read_fwf, write_fwf, fwf_empty, fwf_positions, fwf_positions, read_sav, read_sas, read_dta, write_sav, write_sas, 
- write_dta, read_arrow, write_arrow, read_parquet, write_parquet, read_csv2
+ write_dta, read_arrow, write_arrow, read_parquet, write_parquet, read_csv2, read_file, write_file, read_rdata
 
 
 include("docstrings.jl")
@@ -23,6 +24,7 @@ include("xlfiles.jl")
 include("statsfiles.jl")
 include("parquet_files.jl")
 include("arrow_files.jl")
+include("r_data.jl")
 
 """
 $docstring_read_csv
@@ -444,4 +446,6 @@ function write_table(
         threaded = num_threads > 1)
 end
 
+include("gen_fxn.jl")
+
 end