first five of zipcode and RAM check; closes #5; closes #6 (#13)

Dockerfile

@@ -2,7 +2,7 @@ FROM rocker/r-ver:4.1.3
 
 # DeGAUSS container metadata
 ENV degauss_name="postal"
-ENV degauss_version="0.1.3"
+ENV degauss_version="0.1.4"
 ENV degauss_description="normalized and parsed addresses"
 ENV degauss_argument="expand [default: '']"
 

README.md

@@ -8,14 +8,14 @@
 If `my_address_file.csv` is a file in the current working directory with an address column named `address`, then the [DeGAUSS command](https://degauss.org/using_degauss.html#DeGAUSS_Commands):
 
 ```sh
-docker run --rm -v $PWD:/tmp ghcr.io/degauss-org/postal:0.1.3 my_address_file.csv
+docker run --rm -v $PWD:/tmp ghcr.io/degauss-org/postal:0.1.4 my_address_file.csv
 ```
 
-will produce `my_address_file_postal_0.1.3.csv` with added columns:
+will produce `my_address_file_postal_0.1.4.csv` with added columns:
 
 - **`cleaned_address`**: `address` with non-alphanumeric characterics and excess whitespace removed (with `dht::clean_address()`)
 - **`parsed.{address_component}`**: multiple columns, one for each [parsed address component](https://github.com/openvenues/libpostal#parser-labels) (e.g., `parsed.road`, `parsed.state`, `parsed.house_number`)
-- **`parsed_address`**: a "parsed" address created by pasting together available `parsed.house_number`, `parsed.road`, `parsed.city`, `parsed.state`, `parsed.postcode` address components
+- **`parsed_address`**: a "parsed" address created by pasting together available `parsed.house_number`, `parsed.road`, `parsed.city`, `parsed.state`, and the *first five digits* of the `parsed.postcode` address components
 
 ### Optional Argument
 
@@ -24,10 +24,10 @@ After parsing, the parsed addresses can be expanded into [several possible norma
 If any value is provided as an argument (e.g., "expand"), then the [DeGAUSS command](https://degauss.org/using_degauss.html#DeGAUSS_Commands):
 
 ```sh
-docker run --rm -v $PWD:/tmp ghcr.io/degauss-org/postal:0.1.3 my_address_file.csv expand
+docker run --rm -v $PWD:/tmp ghcr.io/degauss-org/postal:0.1.4 my_address_file.csv expand
 ```
 
-will produce `my_address_file_postal_0.1.3_expand.csv` with the above columns *plus*:
+will produce `my_address_file_postal_0.1.4_expand.csv` with the above columns *plus*:
 
 - **`expanded_addresses`**: the expanded addresses for `parsed_address`
 

entrypoint.R

@@ -2,6 +2,8 @@
 
 dht::greeting()
 
+dht::check_ram(4)
+
 doc <- "
       Usage:
       entrypoint.R <filename> [<expand>]
@@ -44,9 +46,13 @@ parsed_address_components <-
 
 d <- dplyr::bind_cols(d, parsed_address_components)
 
+if (!is.null(d$parsed.postcode)) {
+  d$parsed.postcode_five <- substr(d$parsed.postcode, 1, 5)
+}
+
 d <- tidyr::unite(d,
                   col = "parsed_address",
-                  tidyselect::any_of(paste0("parsed.", c("house_number", "road", "city", "state", "postcode"))),
+                  tidyselect::any_of(paste0("parsed.", c("house_number", "road", "city", "state", "postcode_five"))),
                   sep = " ", na.rm = TRUE, remove = FALSE)
 
 ## expanding addresses

test/address.csv

@@ -19,6 +19,7 @@ id,address
 5100020177,"4506 CAMBERWELL RD CINCINNATI, OH 45209"
 5100020177,"4506 CAMBERWELL RD CINCINNATI, OH CINCINNATI, OH 45209"
 55000100212,"5585 FAIRWOOD RD GREEN TOWNSHIP, OH 45239"
+55000100212,"5585 FAIRWOOD RD GREEN TOWNSHIP, OH 45239-8579"
 51000810328,"6628 JULY CT COLERAIN TOWNSHIP, OH 45239"
 61201400371,"5126 BRASHER AV BLUE ASH, OH 45242"
 19200650054,"3708 TAPPAN AV CINCINNATI, OH 45223"