使用java调用Python中部分代码后卡住？
使用Runtime直接执行Python程序，在Python中用 argv[1] 进行接收。
下面附上Python的程序：
spark = SparkSession.builder.appName("Read from Java Backend").master("local[*]").getOrCreate();# 获取传递的参数
comment = sys.argv[1]
# 将JSON字符串转换为Python对象
comment = json.loads(comment)
# 将 comment 列表转换为 RDD
comment_rdd = spark.sparkContext.parallelize(comment)
# 将 RDD 转换为 Dataframe
df = spark.createDataFrame(comment_rdd.map(lambda x: Row(**x)))
# 加载停用词库
stop_words = spark.sparkContext.textFile("C:/Users/10421/Downloads/baidu_stopwords.txt").collect()
# 定义清理文本函数
def clean_text(text):
# 删除非中文字符
text = re.sub('[^\u4e00-\u9fa5]+', '', text)
return text
# 定义过滤停用词函数
def remove_stopwords(words):
return [w for w in words if w not in stop_words]
# 定义中文分词函数
def seg(text):
return jieba.lcut(text)
# 创建UDF
clean_text_udf = udf(clean_text, StringType())
remove_stopwords_udf = udf(remove_stopwords, StringType())
seg_udf = udf(seg,ArrayType(StringType()))
# 清理文本和过滤停用词
df = df.withColumn("comment", clean_text_udf("comment"))
df = df.withColumn("comment", remove_stopwords_udf("comment"))
df = df.select(concat_ws(" ","comment").alias("comment"))
df = df.withColumn("comment", clean_text_udf("comment"))
# 对comment进行分词
df = df.withColumn("words", seg_udf(col("comment")))
df = df.drop("comment")
df = df.select(explode(col("words")).alias("word"))
# 计算每个单词的出现次数
word_count = df.rdd.map(lambda x: (x.word, 1)).reduceByKey(lambda x, y: x + y)
sorted_word_count = word_count.sortBy(lambda x: x[1], ascending=False)
top_20_words = sorted_word_count.take(20)
column = 0
for row in top_20_words:
print(row[column])
这里尝试一步步注释掉找问题，发现从 sorted_word_count 往后的程序就会导致 Java 那里一直卡住。这部分注释掉可正常运行。
以下为Java代码：
@RestController@RequestMapping("py")
public class TransController {
@PostMapping(value = "/run_py_program")
public static String runPyProgram(@RequestBody List<Map<String, Object>> comment) throws Exception {
// 将comment转换为JSON字符串
ObjectMapper mapper = new ObjectMapper();
String jsonComment = mapper.writeValueAsString(comment);
String json2 = jsonComment.replace("\"", "\\\"");
// 执行Python程序，并传递参数
String[] args1 = new String[]{"C:\\Users\\10421\\AppData\\Local\\Microsoft\\WindowsApps\\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\\python.exe", "C:/Users/10421/Desktop/data/ss.py", json2};
Process process = Runtime.getRuntime().exec(args1);
// 获取程序执行结果
InputStream inputStream = process.getInputStream();
BufferedReader reader = new BufferedReader(new InputStreamReader(inputStream,"gb2312"));
StringBuilder resultBuilder = new StringBuilder();
String line;
while ((line = reader.readLine()) != null) {
resultBuilder.append(line);
}
InputStream errorStream = process.getErrorStream();
BufferedReader reader2 = new BufferedReader(new InputStreamReader(errorStream,"gb2312"));
StringBuilder resultBuilder2 = new StringBuilder();
String line2;
while ((line2 = reader2.readLine()) != null) {
resultBuilder2.append(line2);
}
in.close();
int exitValue = process.waitFor();
if (0 != exitValue) {
System.out.println("执行Shell脚本失败. error code is :" + exitValue);
}
System.out.println(resultBuilder);
// 返回程序执行结果
return resultBuilder.toString();
}
}
破案了，是本地跑不动这个，怎么办？
回答：
运行了一下你的代码，发现从sorted_word_count 这个地方开始往后的部分会导致卡住的问题。
可能的原因是编码的问题，改utf-8试试。
@RestController@RequestMapping("py")
public class TransController {
@PostMapping(value = "/run_py_program")
public static String runPyProgram(@RequestBody List<Map<String, Object>> comment) throws Exception {
// 将 comment 转换为 JSON 字符串
ObjectMapper mapper = new ObjectMapper();
String jsonComment = mapper.writeValueAsString(comment);
String json2 = jsonComment.replace("\"", "\\\"");
// 执行 Python 程序，并传递参数
String[] args1 = new String[]{"python", "C:/Users/10421/Desktop/data/ss.py", json2};
Process process = Runtime.getRuntime().exec(args1);
// 获取程序执行结果
InputStream inputStream = process.getInputStream();
BufferedReader reader = new BufferedReader(new InputStreamReader(inputStream, "UTF-8"));
StringBuilder resultBuilder = new StringBuilder();
String line;
while ((line = reader.readLine()) != null) {
resultBuilder.append(line);
}
InputStream errorStream = process.getErrorStream();
BufferedReader reader2 = new BufferedReader(new InputStreamReader(errorStream, "UTF-8"));
StringBuilder resultBuilder2 = new StringBuilder();
String line2;
while ((line2 = reader2.readLine()) != null) {
resultBuilder2.append(line2);
}
int exitValue = process.waitFor();
if (0 != exitValue) {
System.out.println("执行Shell脚本失败. error code is :" + exitValue);
}
System.out.println(resultBuilder);
// 返回程序执行结果
return resultBuilder.toString();
}
}
以上是 使用java调用Python中部分代码后卡住？ 的全部内容， 来源链接： utcz.com/p/938937.html
