Cookbook regexp2

data/cookbook/regex-misc/00-str.ml

@@ -0,0 +1,31 @@
+---
+packages: []
+discussion: |
+  - **Understanding `Str`: `str` is a library that comes with OCaml. It contains many functions that deal with regular expression. The documentation of the `Str` module is in the [API reference](https://v2.ocaml.org/api/Str.html).
+  - **Alternative Libraries:** The `re` packages provide regular expression functions and supports multiple `regexp` syntaxes (Perl, Posix, Emacs, and Glob). Its functions are also purely functionnal (on the opposite, the `Str.matched_group` and `Str.matched_string` use a global state that prevents the concurrent use of two `regexp` matching sequences). Other packages provide `regexp` functions: `mikmatch`, `ocamlregexkit`, `ppx_regexp`, `pcre`/`pcre2` (compatible with Perl `regexp`), `re2`, `re_parser`, `tyre` (which comes with a PPX preprocessor `ppx_tyre`), and `human-re`. The `ppx-tyre` package defines a `function%tyre` keywork. It works as a native OCaml pattern matching, but on regular expressions. `ppx_regexp` works in the same way with package `re`.
+---
+
+(* Compiling a regular expression: Note, the `{regexp|...|regexp}` is a normal string. This syntax avoids the quoting of `\\`. Indicating `regexp` is optional, but it indicates to the code reader that the string contains a regular expression. *)
+    let regexp = Str.regexp {regexp|\([0-9]+\)-\([0-9]+\)-\([0-9]+\)|regexp}
+
+(* Testing if a string matches the `regexp`: The index (0) indicates the characters from which the matching is performed. `string_match` only matches regular expressions with the string at the given index, while `search_forward` will try to match it at the given index and at the following indexes: *)
+    let () =
+      if Str.string_match regexp "1971-01-23" 0 then
+          print_string "The string match\n"
+      else
+          print_string "The string doesn't match\n"
+    let () =
+      let str = "Date: 1971-01-23" in
+      let index = Str.search_forward regexp str 0 in
+      Printf.printf "Date found at index %d (%s)\n" index
+        (Str.matched_string str)
+
+(* Getting group substring: Each `\\(` / `\\)` pair permits you to get the substring corresponding to the enclosed `regexp`. By convention, the group 0 is the whole substring matching the `regexp`, and the first explicit group is 1: *)
+    let () =
+      let str = "Date: 1971-01-23" in
+      let _index = Str.search_forward regexp str 0 in
+      let year = Str.matched_group 1 str
+      and month = Str.matched_group 2 str
+      and day = Str.matched_group 3 str in
+      Printf.printf "year=%s, month=%s, day=%s\n" year month day
+

data/cookbook/regex-misc/01-ppx_regexp.ml

@@ -0,0 +1,37 @@
+---
+packages:
+- name: "ppx_regexp"
+  tested_version: "0.5.1"
+  used_libraries:
+  - ppx_regexp
+- name: "re"
+  tested_version: "1.10.4"
+  used_libraries:
+  - re
+discussion: |
+  - **Understanding `re`:** The `re` library proposes multiple advantages over the `Str` library, which is shipped with OCaml. It supports multiple syntaxes, and its absence of global states permits concurrent pattern matching. It is completed by the `ppx_regexp`, which makes using this library easier. However, only the PCRE syntax is supported.
+  - **Reference:** `ppx_regexp` is described on [its page](https://github.com/paurkedal/ppx_regexp). It can be completed by the [PCRE syntax](https://www.pcre.org/original/doc/html/pcresyntax.html) or any [PCRE cheat sheet](https://www.debuggex.com/cheatsheet/regex/pcre).
+---
+
+(* In order to match a string with a regular expression, we use the `match%pcre` keyword in a way similar to the OCaml `match`: *)
+
+let () =
+  match%pcre "Date: 1972-01-23  " with
+  | {re|?<date>(?<year>\d{4})-(?<month>\d\d)-(?<day>\d\d)|re} ->
+      Printf.printf "Date found: (%s)\n" date;
+      Printf.printf "Year: (%s)\n" year;
+      Printf.printf "Month: (%s)\n" month;
+      Printf.printf "Day: (%s)\n" day;
+  | _ -> print_string "Date not found\n"
+
+(* In a similar way, we have a `function%pcre` with perform similar tasks *)
+
+let all_digits =
+  function%pcre
+  | {re|^\d*$|re} -> true
+  | _ -> false
+
+let () =
+  assert (all_digits "1234")
+let () =
+  assert (not @@ all_digits "12x34")

data/cookbook/tasks.yml

@@ -18,7 +18,7 @@ categories:
       C library, using the OCaml foreign function interface.
 - title: Compression
   tasks:
-  - title: Read a gzip compressed text file
+  - title: Read a gzip Compressed Text File
     slug: read-gzip-text-file
   - title: Decompressing a Tarball
     slug: decompressing-a-tarball
@@ -30,7 +30,7 @@ categories:
     tasks:
     - title: Create and Await Promises
       slug: create-and-await-promises
-  - title: Parallelism & Multi-Threading
+  - title: Parallelism & Multithreading
     tasks:
     - title: Spawn a Thread and Receive a Response
       slug: spawn-a-thread-and-receive-a-response
@@ -40,9 +40,9 @@ categories:
   tasks:
   - title: Calculate the SHA-256 Digest of a File
     slug: calculate-sha-256-digest-of-file
-  - title: Sign and Verify a Message with an HMAC Digest
+  - title: Sign and Verify a Message With an HMAC Digest
     slug: sign-and-verify-hmac-digest
-  - title: Salt and Hash a Password with PBKDF2
+  - title: Salt and Hash a Password With PBKDF2
     slug: salt-and-hash-password-with-pkgdf2
 - title: Data Structures & Algorithms
   subcategories:
@@ -105,23 +105,23 @@ categories:
 
   - title: Display Formatted Date and Time
     slug: display-formatted-date-time
-  - title: Parse Date and Time from String
+  - title: Parse Date and Time From String
     slug: parse-date-time-from-string
 - title: Debugging
   tasks:
   - title: Debug Print a Value
     slug: debug-print-a-value
   - title: Log a Debug / Error Message to Stdout / Stderr
     slug: log-debug-error-message
-  - title: Log to the UNIX Syslog
+  - title: Log to the Unix Syslog
     slug: log-to-unix-syslog
 - title: Encoding
   tasks:
   - title: URL- / Percent-Encode a String
     slug: url-percent-encode-string
   - title: Encode a String as application/x-www-form-urlencoded
     slug: encode-x-www-form-urlencoded
-  - title: Encode and Decode Bytestrings from Hex-Strings
+  - title: Encode and Decode Bytestrings From Hex-Strings
     slug: encode-decode-hex
   - title: Encode and Decode Base64
     slug: encode-decode-base64
@@ -176,7 +176,7 @@ categories:
   subcategories:
   - title: Vector & Matrix Operations
     tasks:
-    - title: Normalize a Vector
+    - title: Normalise a Vector
       slug: normalize-vector
     - title: Matrix Addition and Multiplication
       slug: matrix-addition-multiplication
@@ -214,47 +214,49 @@ categories:
       slug: regex-validate-email
     - title: Extract Phone Numbers from Text
       slug: regex-extract-phone-numbers
-    - title: Replace All Occurrences of a Text Pattern with Another Pattern
+    - title: Replace All Occurrences of a Text Pattern With Another Pattern
       slug: regex-replace-pattern
+    - title: Miscellaneous
+      slug: regex-misc
 - title: Web Programming
   subcategories:
   - title: HTTP Clients
     tasks:
-    - title: Make a HTTP GET Request
+    - title: Make an HTTP GET Request
       slug: make-http-get-request
       description: >
         Make an HTTP GET request, process response code, follow redirects
-    - title: Make a HTTP GET Request with Basic Authentication
+    - title: Make an HTTP GET Request With Basic Authentication
       slug: make-http-get-basic-auth
     - title: Download a File to a Temporary Directory
       slug: download-file-to-temporary-dir
-    - title: Make a Partial Download with HTTP Range Header
+    - title: Make a Partial Download With HTTP Range Header
       slug: make-partial-download-with-http-range-header
-  - title: Dealing with HTML
+  - title: Dealing With HTML
     tasks:
-    - title: Render a HTML Template
+    - title: Render an HTML Template
       slug: render-html-template
-    - title: Extract all Links from a HTML String
+    - title: Extract All Links From an HTML String
       slug: extract-links-from-html
     - title: Check a Webpage for Broken Links
       slug: check-webpage-for-broken-links
   - title: Running a Web Server
     tasks:
-    - title: Start a Web Server with a Hello World Endpoint
+    - title: Start a Web Server With a "Hello World" Endpoint
       slug: start-a-web-server-hello-world
     - title: Start a Web Server that Serves a HTML Template
       slug: start-a-web-server-html-template
     - title: Use Basic Authentication to Secure a Route
       slug: use-basic-auth-on-web-server
   - title: Media Types (MIME)
     tasks:
-    - title: Get MIME Type from String
+    - title: Get MIME Type From String
       slug: get-mime-type-from-string
-    - title: Get MIME Type from Filename
+    - title: Get MIME Type From Filename
       slug: get-mime-type-from-filename
-    - title: Parse MIME Type of a HTTP Response
+    - title: Parse MIME Type of an HTTP Response
       slug: parse-mime-type-of-http-response
-  - title: URL and URI processing
+  - title: URL and URI Processing
     tasks:
-    - title: Parse a URL from String And Access Individual Parts
+    - title: Parse a URL From String and Access Individual Parts
       slug: parse-url-from-string