boost/website-v2-docs
2
0
Fork 0
mirror of https://github.com/boostorg/website-v2-docs.git synced 2026-01-19 04:42:17 +00:00
Code Issues Projects Releases Wiki Activity

Text Processing scenario updated (#497)

Browse Source
This commit is contained in:
Peter Turcan
2025-09-04 11:34:01 -07:00
committed by GitHub
parent f95913ee08
commit 126d849c83
1 changed files with 151 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files

191
user-guide/modules/ROOT/pages/task-text-processing.adoc
View File

@@ -16,6 +16,7 @@ Developing a word processor, or other text based app, involves handling text, GU
* <<Sample of Regular Expression Parsing>>
* <<Add Robust Date and Time Parsing>>
* <<Culturally Aware Date Formatting>>
* <<Local Time>>
* <<See Also>>
== Libraries
@@ -60,8 +61,6 @@ We'll write a program that scans a string for dates in the format "YYYY-MM-DD" a
[source,cpp]
----
#include <iostream>
#include <string>
#include <vector>
#include <boost/regex.hpp>
#include <boost/algorithm/string.hpp>
@@ -92,9 +91,9 @@ void find_dates(const std::string& text) {
int day = std::stoi(match[3]);
if (is_valid_date(year, month, day)) {
std::cout << "✅ Valid date found: " << match[0] << "\n";
std::cout << "Valid date found: " << match[0] << "\n";
} else {
std::cout << "❌ Invalid date: " << match[0] << " (Incorrect month/day)\n";
std::cout << "Invalid date: " << match[0] << " (Incorrect month/day)\n";
}
start = match[0].second; // Move to next match
@@ -102,7 +101,7 @@ void find_dates(const std::string& text) {
}
if (!found) {
std::cout << "⚠️ No valid dates found in the input text.\n";
std::cout << "No valid dates found in the input text.\n";
}
}
@@ -123,8 +122,8 @@ The following shows a successful parse:
----
Enter a sentence containing dates (YYYY-MM-DD format):
Today is 2024-02-19, and tomorrow is 2024-02-20.
✅ Valid date found: 2024-02-19
✅ Valid date found: 2024-02-20
Valid date found: 2024-02-19
Valid date found: 2024-02-20
----
@@ -134,11 +133,11 @@ And the following shows several unsuccessful parses:
----
Enter a sentence containing dates (YYYY-MM-DD format):
The deadline is 2024-02-30.
❌ Invalid date: 2024-02-30 (Incorrect month/day)
Invalid date: 2024-02-30 (Incorrect month/day)
Enter a sentence containing dates (YYYY-MM-DD format):
There are no dates in this sentence.
⚠️ No valid dates found in the input text.
No valid dates found in the input text.
----
@@ -148,11 +147,7 @@ The clunky date validation in the sample above can be improved by integrating bo
[source,cpp]
----
#include <iostream>
#include <string>
#include <vector>
#include <boost/regex.hpp>
#include <boost/algorithm/string.hpp>
#include <boost/date_time/gregorian/gregorian.hpp>
namespace greg = boost::gregorian;
@@ -162,7 +157,8 @@ bool is_valid_date(int year, int month, int day) {
try {
greg::date test_date(year, month, day);
return true; // If no exception, it's valid
} catch (const std::exception& e) {
}
catch (const std::exception& e) {
return false; // Invalid date
}
}
@@ -182,9 +178,10 @@ void find_dates(const std::string& text) {
if (is_valid_date(year, month, day)) {
greg::date valid_date(year, month, day);
std::cout << "✅ Valid date found: " << valid_date << "\n";
} else {
std::cout << "❌ Invalid date: " << match[0] << " (Does not exist)\n";
std::cout << "Valid date found: " << valid_date << "\n";
}
else {
std::cout << "Invalid date: " << match[0] << " (Does not exist)\n";
}
start = match[0].second; // Move to next match
@@ -192,7 +189,7 @@ void find_dates(const std::string& text) {
}
if (!found) {
std::cout << "⚠️ No valid dates found in the input text.\n";
std::cout << "No valid dates found in the input text.\n";
}
}
@@ -200,7 +197,7 @@ int main() {
std::string input;
std::cout << "Enter a sentence containing dates (YYYY-MM-DD format):\n";
std::getline(std::cin, input);
find_dates(input);
return 0;
}
@@ -215,8 +212,8 @@ The following shows a successful parse:
----
Enter a sentence containing dates (YYYY-MM-DD format):
Today is 2024-02-29, and tomorrow is 2024-03-01.
✅ Valid date found: 2024-Feb-29
✅ Valid date found: 2024-Mar-01
Valid date found: 2024-Feb-29
Valid date found: 2024-Mar-01
----
@@ -228,12 +225,12 @@ And the following shows several unsuccessful parses:
----
Enter a sentence containing dates (YYYY-MM-DD format):
The deadline is 2024-02-30.
❌ Invalid date: 2024-02-30 (Does not exist)
Invalid date: 2024-02-30 (Does not exist)
Enter a sentence containing dates (YYYY-MM-DD format):
There are no dates in this sentence.
⚠️ No valid dates found in the input text.
No valid dates found in the input text.
----
@@ -248,11 +245,8 @@ Dates are not represented consistently across the globe. Let's use boost:locale[
[source,cpp]
----
#include <iostream>
#include <string>
#include <vector>
#include <boost/regex.hpp>
#include <boost/algorithm/string.hpp>
#include <boost/date_time/gregorian/gregorian.hpp>
#include <boost/locale.hpp>
@@ -264,7 +258,8 @@ bool is_valid_date(int year, int month, int day) {
try {
greg::date test_date(year, month, day);
return true; // If no exception, it's valid
} catch (const std::exception&) {
}
catch (const std::exception&) {
return false; // Invalid date
}
}
@@ -274,8 +269,8 @@ void display_localized_date(const greg::date& date, const std::string& locale_na
std::locale locale = loc::generator().generate(locale_name);
std::cout.imbue(locale); // Apply locale to std::cout
std::cout << "🌍 " << locale_name << " formatted date: "
<< loc::as::date << date << "\n";
std::cout << locale_name << " formatted date: "
<< loc::as::date << date << "\n";
}
// Function to find and validate dates in a text
@@ -293,10 +288,11 @@ void find_dates(const std::string& text, const std::string& locale_name) {
if (is_valid_date(year, month, day)) {
greg::date valid_date(year, month, day);
std::cout << "✅ Valid date found: " << valid_date << "\n";
std::cout << "Valid date found: " << valid_date << "\n";
display_localized_date(valid_date, locale_name);
} else {
std::cout << "❌ Invalid date: " << match[0] << " (Does not exist)\n";
}
else {
std::cout << "Invalid date: " << match[0] << " (Does not exist)\n";
}
start = match[0].second; // Move to next match
@@ -304,7 +300,7 @@ void find_dates(const std::string& text, const std::string& locale_name) {
}
if (!found) {
std::cout << "⚠️ No valid dates found in the input text.\n";
std::cout << "No valid dates found in the input text.\n";
}
}
@@ -333,14 +329,14 @@ The following shows successful parses:
Enter a sentence containing dates (YYYY-MM-DD format):
The meeting is on 2024-03-15.
Enter your preferred locale (e.g., en_US.UTF-8, fr_FR.UTF-8, de_DE.UTF-8): en_US.UTF-8
✅ Valid date found: 2024-Mar-15
🌍 en_US.UTF-8 formatted date: March 15, 2024
Valid date found: 2024-Mar-15
en_US.UTF-8 formatted date: March 15, 2024
Enter a sentence containing dates (YYYY-MM-DD format):
Rendez-vous le 2024-07-20.
Enter your preferred locale (e.g., en_US.UTF-8, fr_FR.UTF-8, de_DE.UTF-8): fr_FR.UTF-8
✅ Valid date found: 2024-Jul-20
🌍 fr_FR.UTF-8 formatted date: 20 juillet 2024
Valid date found: 2024-Jul-20
fr_FR.UTF-8 formatted date: 20 juillet 2024
----
@@ -351,11 +347,126 @@ And the following shows an unsuccessful parse:
Enter a sentence containing dates (YYYY-MM-DD format):
The deadline is 2024-02-30.
Enter your preferred locale (e.g., en_US.UTF-8, fr_FR.UTF-8, de_DE.UTF-8): en_US.UTF-8
❌ Invalid date: 2024-02-30 (Does not exist)
Invalid date: 2024-02-30 (Does not exist)
----
For a boost:spirit[] approach to parsing, refer to xref:task-natural-language-parsing.adoc[].
== Local Time
On a similar global vein, when you install the boost:date_time[] library (or all the Boost libraries), a file containing definitions of time zones across the world is available for your use at: `boost_<version>\\libs\\date_time\\data\\date_time_zonespec.csv`.
The following short sample shows how to use the contents of the file. Enter a city and timezone in the IANA format (such as: 'Europe/Berlin' or 'Asia/Tokyo'), and the current date and time will be output.
[source,cpp]
----
#include <boost/date_time/local_time/local_time.hpp>
namespace pt = boost::posix_time;
namespace lt = boost::local_time;
int main() {
try {
//---------------------------------------------
// Load the Boost tz_database from CSV
//---------------------------------------------
lt::tz_database tz_db;
tz_db.load_from_file("<YOUR PATH>\\date_time_zonespec.csv"); // Adjust the path to your Boost installation
// Extract all valid timezone names
std::vector<std::string> valid_timezones;
for (const auto& tz_name : tz_db.region_list()) {
valid_timezones.push_back(tz_name);
}
std::string city;
while (true) {
std::cout << "\nEnter 'city/timezone' (or 'exit' to quit, or 'zones' for list of options): ";
std::getline(std::cin, city);
if (city == "exit") break;
if (city == "zones")
{
std::cout << "Available timezones:\n";
for (const auto& tz : valid_timezones) {
std::cout << tz << "\n";
}
}
else
{
// Find the timezone (case-sensitive, must match CSV)
lt::time_zone_ptr tz = tz_db.time_zone_from_region(city);
if (!tz) {
std::cout << "Invalid timezone! Try again.\n";
continue;
}
// Get current UTC time
pt::ptime utc_now = pt::second_clock::universal_time();
// Convert UTC to local time in the chosen timezone
lt::local_date_time local_now(utc_now, tz);
// Get user's local machine time
pt::ptime user_now = pt::second_clock::local_time();
std::cout << "\nYour local system time: " << user_now << "\n";
std::cout << "Current local time in " << city << ": " << local_now << "\n";
}
}
}
catch (const std::exception& e) {
std::cerr << "Fatal error: " << e.what() << "\n";
return 1;
}
return 0;
}
----
Run the program and test out a few options:
[source,text]
----
Enter 'city/timezone' (or 'exit' to quit, or 'zones' for list of options): America/New_York
Your local system time: 2025-Sep-03 16:38:02
Current local time in America/New_York: 2025-Sep-03 19:38:02 EDT
Enter 'city/timezone' (or 'exit' to quit, or 'zones' for list of options): Antarctica/South_Pole
Your local system time: 2025-Sep-03 16:38:20
Current local time in Antarctica/South_Pole: 2025-Sep-04 11:38:20 NZST
Enter 'city/timezone' (or 'exit' to quit, or 'zones' for list of options): zones
Available timezones:
Africa/Abidjan
Africa/Accra
Africa/Addis_Ababa
Africa/Algiers
Africa/Asmara
Africa/Asmera
Africa/Bamako
Africa/Bangui
Africa/Banjul
Africa/Bissau
Africa/Blantyre
Africa/Brazzaville
Africa/Bujumbura
Africa/Cairo
Africa/Casablanca
Africa/Ceuta
Africa/Conakry
....
----
== Next Steps
If more complex input is required, consider the boost:spirit[] approach to parsing, refer to xref:task-natural-language-parsing.adoc[].
== See Also