Question

我正在尝试创建一个程序，其中文本输出到控制台，具有字符延迟。（另外，我对此很陌生，所以我对 cout 的工作原理并不十分了解。）

#__________________________________________________________________________________________________________________________________

# Set parameters used for filtering rows
#__________________________________________________________________________________________________________________________________

firstDate <- '2017-07-01'
maxDate <- '2017-08-31'
advertiserID <- '4529611'
advertiserID2 <- '4601141'
advertiserID3 <- '4601141'

library(dplyr)
library(stringr)
library(sparklyr)

#__________________________________________________________________________________________________________________________________

# Configure & connect to spark
#__________________________________________________________________________________________________________________________________

Sys.setenv("SPARK_MEM"="100g")
Sys.setenv(HADOOP_HOME="C:/Users/Jay.Ruffell/AppData/Local/rstudio/spark/Cache/spark-2.0.1-bin-hadoop2.7/tmp/hadoop") 

config <- spark_config()
config$sparklyr.defaultPackages <- "org.apache.hadoop:hadoop-aws:2.7.3" # used to connect to S3
Sys.setenv(AWS_ACCESS_KEY_ID="")
Sys.setenv(AWS_SECRET_ACCESS_KEY="") # setting these blank ensures that AWS uses the IAM roles associated with the cluster to define S3 permissions

# Specify memory parameters - have tried lots of different values here!
config$`sparklyr.shell.driver-memory` <- '50g' 
config$`sparklyr.shell.executor-memory` <- '50g'
config$spark.driver.maxResultSize <- '50g'
sc <- spark_connect(master='local', config=config, version='2.0.1')

#__________________________________________________________________________________________________________________________________

# load data into spark from S3 ----
#__________________________________________________________________________________________________________________________________

#+++++++++++++++++++
# create spark table (not in memory yet) of all logfiles within logfiles path
#+++++++++++++++++++

spark_session(sc) %>%
  invoke("read") %>% 
  invoke("format", "orc") %>%
  invoke("load", 's3a://nz-omg-ann-aipl-data-lake/aip-connect-256537/orc-files/dcm-log-files/dt2-facts') %>% 
  invoke("createOrReplaceTempView", "alldatadf") 
alldftbl <- tbl(sc, 'alldatadf') # create a reference to the sparkdf without loading into memory

#+++++++++++++++++++
# define variables used to filter table down to daterange
#+++++++++++++++++++

# Calculate firstDate & maxDate as unix timestamps
unixTime_firstDate <- as.numeric(as.POSIXct(firstDate))+1
unixTime_maxDate <- as.numeric(as.POSIXct(maxDate)) + 3600*24-1

# Convert daterange params into date_year, date_month & date_day values to pass to filter statement
dateRange <- as.character(seq(as.Date(firstDate), as.Date(maxDate), by=1))
years <- unique(substring(dateRange, first=1, last=4))
if(length(years)==1) years <- c(years, years)
year_y1 <- years[1]; year_y2 <- years[2]
months_y1 <- substring(dateRange[grepl(years[1], dateRange)], first=6, last=7)
minMonth_y1 <- min(months_y1)
maxMonth_y1 <- max(months_y1)
months_y2 <- substring(dateRange[grepl(years[2], dateRange)], first=6, last=7)
minMonth_y2 <- min(months_y2)
maxMonth_y2 <- max(months_y2) 

# Repeat for 1 day prior to first date & one day after maxdate (because of the way logfile orc partitions are created, sometimes touchpoints can end up in the wrong folder by 1 day. So read in extra days, then filter by event time)
firstDateMinusOne <- as.Date(firstDate)-1
firstDateMinusOne_year <- substring(firstDateMinusOne, first=1, last=4)
firstDateMinusOne_month <- substring(firstDateMinusOne, first=6, last=7) 
firstDateMinusOne_day <- substring(firstDateMinusOne, first=9, last=10)
maxDatePlusOne <- as.Date(maxDate)+1
maxDatePlusOne_year <- substring(maxDatePlusOne, first=1, last=4)
maxDatePlusOne_month <- substring(maxDatePlusOne, first=6, last=7)
maxDatePlusOne_day <- substring(maxDatePlusOne, first=9, last=10)

#+++++++++++++++++++
# Read in data, filter & select
#+++++++++++++++++++

# startTime <- proc.time()[3]
dftbl <- alldftbl %>% # create a reference to the sparkdf without loading into memory

  # filter by month and year, using ORC partitions for extra speed
  filter(((date_year==year_y1  & date_month>=minMonth_y1 & date_month<=maxMonth_y1) |
            (date_year==year_y2 & date_month>=minMonth_y2 & date_month<=maxMonth_y2) |
            (date_year==firstDateMinusOne_year & date_month==firstDateMinusOne_month & date_day==firstDateMinusOne_day) |
            (date_year==maxDatePlusOne_year & date_month==maxDatePlusOne_month & date_day==maxDatePlusOne_day))) %>%

  # filter to be within firstdate & maxdate. Note that event_time_char will be in UTC, so 12hrs behind.
  filter(event_time>=(unixTime_firstDate*1000000) & event_time<(unixTime_maxDate*1000000)) %>%

  # filter by advertiser ID
  filter(((advertiser_id==advertiserID | advertiser_id==advertiserID2 | advertiser_id==advertiserID3) & 
            !is.na(advertiser_id)) |
           ((floodlight_configuration==advertiserID | floodlight_configuration==advertiserID2 | 
               floodlight_configuration==advertiserID3) & !is.na(floodlight_configuration)) & user_id!="0") %>%

  # Define cols to keep
  transmute(time=as.numeric(event_time/1000000),
            user_id=as.character(user_id),
            action_type=as.character(if(fact_type=='click') 'C' else if(fact_type=='impression') 'I' else if(fact_type=='activity') 'A' else NA),
            lookup=concat_ws("_", campaign_id, ad_id, site_id_dcm, placement_id),
            activity_lookup=as.character(activity_id),
            sv1=as.character(segment_value_1),
            other_data=as.character(other_data))  %>%
  mutate(time_char=as.character(from_unixtime(time)))

# cache to memory
dftbl <- sdf_register(dftbl, "filtereddf")
tbl_cache(sc, "filtereddf")

#__________________________________________________________________________________________________________________________________

# Collect out of spark
#__________________________________________________________________________________________________________________________________

myDF <- collect(dftbl)

运行此代码时，控制台会等待4秒钟，然后将Llama打印到控制台。

如果你在字符串的末尾添加\ n字符，这会产生不良输出。

int main() {
  std::cout << "L";
  waitms(1000); //function that pauses 1 second.
  std::cout << "l";
  waitms(1000);
  std::cout << "a";
  waitms(1000);
  std::cout << "m";
  waitms(1000);
  std::cout << "a";
}

有没有办法在没有换行符的情况下弹出流？

Answer 1

您需要刷新输出，例如std::flush：

include:
  - assets

std::cout << "L" << std::flush; waitms(1000); std::cout << "l" << std::flush; // ... etc ...通常会缓冲控制台输出。通过std::cout打印换行符通常会刷新输出，'\n'始终会刷新。这就是您通常不会注意到的原因。但是如果你想延迟在一行上打印东西，你需要手动刷新控制台输出。

Answer 2

我发现了类似的东西，但使用了 #include <windows.h> 标头。但我正在寻找一种更快的方法.. 是否有一个函数可以让您编写整个字符串并让该函数为您切碎它，这样您就不必在字母之间编写所有这些代码？我知道有，但我无法自己弄清楚......这是我写的：

cout << "R"; Sleep(300); cout << "E"; Sleep(300); cout << "C"; Sleep(300); cout << "U"; Sleep(300); cout << "R"; Sleep(300); cout << "S"; Sleep(300); cout << "I"; Sleep(300); cout << "V"; Sleep(300); cout << "E           "; Sleep(300); cout << "F"; Sleep(300); cout << "U"; Sleep(300); cout << "N"; Sleep(300); cout << "C"; Sleep(300); cout << "T"; Sleep(300); cout << "I"; Sleep(300); cout << "O"; Sleep(300); cout << "N" << endl;
Sleep(300);
cout << "***********************************************************";
Sleep(800); cout << endl << "What "; Sleep(800); cout << "Is "; Sleep(800); cout << "It?" << endl;
Sleep(2000);
cout << "      It is a function that calls itself. " << endl; Sleep(500); cout << "            To avoid having this function run indefinitely, you must inclue a termination condition" << endl << endl;
Sleep(1000); 
cout << "               (kinda reminds me of a for loop, doesn't it?)" << endl;

按延迟字符打印单词字符

2 个答案: